Sergey Levine

Orcid: 0000-0001-6764-2743

According to our database1, Sergey Levine authored at least 586 papers between 2009 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
SACSoN: Scalable Autonomous Control for Social Navigation.
IEEE Robotics Autom. Lett., January, 2024

Multistage Cable Routing Through Hierarchical Imitation Learning.
IEEE Trans. Robotics, 2024

LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos.
CoRR, 2024

KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data.
CoRR, 2024

Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation.
CoRR, 2024

Unsupervised-to-Online Reinforcement Learning.
CoRR, 2024

Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation.
CoRR, 2024

Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding.
CoRR, 2024

Autonomous Improvement of Instruction Following Skills via Foundation Models.
CoRR, 2024

Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review.
CoRR, 2024

Video Occupancy Models.
CoRR, 2024

Robotic Control via Embodied Chain-of-Thought Reasoning.
CoRR, 2024

Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs.
CoRR, 2024

HiLMa-Res: A General Hierarchical Framework via Residual RL for Combining Quadrupedal Locomotion and Manipulation.
CoRR, 2024

Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models.
CoRR, 2024

Adding Conditional Control to Diffusion Models with Reinforcement Learning.
CoRR, 2024

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.
CoRR, 2024

Is Value Learning Really the Main Bottleneck in Offline RL?
CoRR, 2024

OpenVLA: An Open-Source Vision-Language-Action Model.
CoRR, 2024

Language Guided Skill Discovery.
CoRR, 2024

Strategically Conservative Q-Learning.
CoRR, 2024

Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models.
CoRR, 2024

Octo: An Open-Source Generalist Robot Policy.
CoRR, 2024

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning.
CoRR, 2024

Evaluating Real-World Robot Manipulation Policies in Simulation.
CoRR, 2024

RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes.
CoRR, 2024

Learning Visuotactile Skills with Two Multifingered Hands.
CoRR, 2024

Autonomous Evaluation and Refinement of Digital Agents.
CoRR, 2024

Yell At Your Robot: Improving On-the-Fly from Language Corrections.
CoRR, 2024

Unfamiliar Finetuning Examples Control How Language Models Hallucinate.
CoRR, 2024

Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference.
CoRR, 2024

MOKA: Open-Vocabulary Robotic Manipulation through Mark-Based Visual Prompting.
CoRR, 2024

SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation.
CoRR, 2024

Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation.
CoRR, 2024

Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control.
CoRR, 2024

Vision-Language Models Provide Promptable Representations for Reinforcement Learning.
CoRR, 2024

Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control.
CoRR, 2024

AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents.
CoRR, 2024

FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning.
CoRR, 2024

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization.
CoRR, 2024

D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning.
Proceedings of the 1st Reinforcement Learning Conference, 2024

NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Robotic Offline RL from Internet Videos via Value-Function Learning.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Learning to Explore in POMDPs with Informational Rewards.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Feedback Efficient Online Fine-Tuning of Diffusion Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Foundation Policies with Hilbert Representations.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

RLIF: Interactive Imitation Learning as Reinforcement Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Deep Neural Networks Tend To Extrapolate Predictably.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

The False Promise of Imitating Proprietary Language Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Training Diffusion Models with Reinforcement Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Defining Deception in Decision Making.
Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023
Improving Generalization with Approximate Factored Value Functions.
Trans. Mach. Learn. Res., 2023

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models.
CoRR, 2023

Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations.
CoRR, 2023

Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment.
CoRR, 2023

Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models.
CoRR, 2023

Latent Conservative Objective Models for Data-Driven Crystal Structure Prediction.
CoRR, 2023

Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias.
CoRR, 2023

Robotic Offline RL from Internet Videos via Value-Function Pre-Training.
CoRR, 2023

A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning.
CoRR, 2023

Multi-Stage Cable Routing through Hierarchical Imitation Learning.
CoRR, 2023

Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts.
CoRR, 2023

Stabilizing Contrastive RL: Techniques for Offline Goal Reaching.
CoRR, 2023

SACSoN: Scalable Autonomous Data Collection for Social Navigation.
CoRR, 2023

The False Promise of Imitating Proprietary LLMs.
CoRR, 2023

Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators.
CoRR, 2023

IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies.
CoRR, 2023

Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement.
CoRR, 2023

Ignorance is Bliss: Robust Control via Information Gating.
CoRR, 2023

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning.
CoRR, 2023

Grounded Decoding: Guiding Text Generation with Grounded Models for Robot Control.
CoRR, 2023

Robust and Versatile Bipedal Jumping Control through Multi-Task Reinforcement Learning.
CoRR, 2023

Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features.
CoRR, 2023

Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware.
Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023

Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models.
Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023

Learning and Adapting Agile Locomotion Skills by Transferring Experience.
Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023

Robust and Versatile Bipedal Jumping Control through Reinforcement Learning.
Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023

Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials.
Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023

Demonstrating A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning.
Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023



Ignorance is Bliss: Robust Control via Information Gating.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

HIQL: Offline Goal-Conditioned RL with Latent States as Actions.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Accelerating Exploration with Unlabeled Prior Data.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Learning to Influence Human Behavior with Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Multi-Task Imitation Learning for Linear Dynamical Systems.
Proceedings of the Learning for Dynamics and Control Conference, 2023

Contrastive Example-Based Control.
Proceedings of the Learning for Dynamics and Control Conference, 2023

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios.
IROS, 2023

Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning.
IROS, 2023

Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

GNM: A General Navigation Model to Drive Any Robot.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Adversarial Policies Beat Superhuman Go AIs.
Proceedings of the International Conference on Machine Learning, 2023

Jump-Start Reinforcement Learning.
Proceedings of the International Conference on Machine Learning, 2023

Predictable MDP Abstraction for Unsupervised Model-Based RL.
Proceedings of the International Conference on Machine Learning, 2023

Understanding the Complexity Gains of Single-Task RL with a Curriculum.
Proceedings of the International Conference on Machine Learning, 2023

Reinforcement Learning from Passive Data via Latent Intentions.
Proceedings of the International Conference on Machine Learning, 2023

A Connection between One-Step RL and Critic Regularization in Reinforcement Learning.
Proceedings of the International Conference on Machine Learning, 2023


Efficient Online Reinforcement Learning with Offline Data.
Proceedings of the International Conference on Machine Learning, 2023

Offline RL for Natural Language Generation with Implicit Language Q Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Efficient Deep Reinforcement Learning Requires Regulating Overfitting.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Confidence-Conditioned Value Functions for Offline Reinforcement Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement.
Proceedings of the Eleventh International Conference on Learning Representations, 2023


BridgeData V2: A Dataset for Robot Learning at Scale.
Proceedings of the Conference on Robot Learning, 2023

FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing.
Proceedings of the Conference on Robot Learning, 2023

ViNT: A Foundation Model for Visual Navigation.
Proceedings of the Conference on Robot Learning, 2023

Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning.
Proceedings of the Conference on Robot Learning, 2023

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control.
Proceedings of the Conference on Robot Learning, 2023

Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning.
Proceedings of the Conference on Robot Learning, 2023

REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation.
Proceedings of the Conference on Robot Learning, 2023


2022
ASE: large-scale reusable adversarial skill embeddings for physically simulated characters.
ACM Trans. Graph., 2022

Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results.
CoRR, 2022

Dual Generator Offline Reinforcement Learning.
CoRR, 2022

Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints.
CoRR, 2022

Adversarial Policies Beat Professional-Level Go AIs.
CoRR, 2022

FCM: Forgetful Causal Masking Makes Causal Language Models Better Zero-Shot Learners.
CoRR, 2022

Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials.
CoRR, 2022

A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning.
CoRR, 2022

Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience.
CoRR, 2022

Multimodal Masked Autoencoders Learn Transferable Representations.
CoRR, 2022

When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?
CoRR, 2022

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.
CoRR, 2022

Fully Online Meta-Learning Without Task Boundaries.
CoRR, 2022

ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints.
Proceedings of the Robotics: Science and Systems XVIII, New York City, NY, USA, June 27, 2022

Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets.
Proceedings of the Robotics: Science and Systems XVIII, New York City, NY, USA, June 27, 2022

MEMO: Test Time Robustness via Adaptation and Augmentation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Adversarial Unlearning: Reducing Confidence Along Adversarial Directions.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Data-Driven Offline Decision-Making via Invariant Representation Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Contrastive Learning as Goal-Conditioned Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Imitating Past Successes can be Very Suboptimal.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Mismatched No More: Joint Model-Policy Optimization for Model-Based RL.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

You Only Live Once: Single-Life Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Distributionally Adaptive Meta Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning.
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

Context-Aware Language Modeling for Goal-Oriented Dialogue Systems.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

Offline Meta-Reinforcement Learning for Industrial Insertion.
Proceedings of the 2022 International Conference on Robotics and Automation, 2022

Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World.
Proceedings of the 2022 International Conference on Robotics and Automation, 2022

Control-Aware Prediction Objectives for Autonomous Driving.
Proceedings of the 2022 International Conference on Robotics and Automation, 2022

Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments.
Proceedings of the 2022 International Conference on Robotics and Automation, 2022

ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning.
Proceedings of the 2022 International Conference on Robotics and Automation, 2022

How to Leverage Unlabeled Data in Offline Reinforcement Learning.
Proceedings of the International Conference on Machine Learning, 2022

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization.
Proceedings of the International Conference on Machine Learning, 2022

Offline Meta-Reinforcement Learning with Online Self-Supervision.
Proceedings of the International Conference on Machine Learning, 2022

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control.
Proceedings of the International Conference on Machine Learning, 2022

Planning with Diffusion for Flexible Behavior Synthesis.
Proceedings of the International Conference on Machine Learning, 2022

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning.
Proceedings of the International Conference on Machine Learning, 2022

Offline RL Policies Should Be Trained to be Adaptive.
Proceedings of the International Conference on Machine Learning, 2022

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks.
Proceedings of the Tenth International Conference on Learning Representations, 2022

TRAIL: Near-Optimal Imitation Learning with Suboptimal Data.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Autonomous Reinforcement Learning: Formalism and Benchmarking.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Extending the WILDS Benchmark for Unsupervised Adaptation.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Data-Driven Offline Optimization for Architecting Hardware Accelerators.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Should I Run Offline Reinforcement Learning or Behavioral Cloning?
Proceedings of the Tenth International Conference on Learning Representations, 2022

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Offline Reinforcement Learning with Implicit Q-Learning.
Proceedings of the Tenth International Conference on Learning Representations, 2022

The Information Geometry of Unsupervised Reinforcement Learning.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Maximum Entropy RL (Provably) Solves Some Robust RL Problems.
Proceedings of the Tenth International Conference on Learning Representations, 2022

RvS: What is Essential for Offline RL via Supervised Learning?
Proceedings of the Tenth International Conference on Learning Representations, 2022

Information Prioritization through Empowerment in Visual Model-based RL.
Proceedings of the Tenth International Conference on Learning Representations, 2022

CoMPS: Continual Meta Policy Search.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning.
Proceedings of the Conference on Robot Learning, 2022

LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action.
Proceedings of the Conference on Robot Learning, 2022

Offline Reinforcement Learning for Visual Navigation.
Proceedings of the Conference on Robot Learning, 2022

Is Anyone There? Learning a Planner Contingent on Perceptual Uncertainty.
Proceedings of the Conference on Robot Learning, 2022


Inner Monologue: Embodied Reasoning through Planning with Language Models.
Proceedings of the Conference on Robot Learning, 2022

GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots.
Proceedings of the Conference on Robot Learning, 2022

Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks.
Proceedings of the Conference on Robot Learning, 2022

2021
AMP: adversarial motion priors for stylized physics-based character control.
ACM Trans. Graph., 2021

LaND: Learning to Navigate From Disengagements.
IEEE Robotics Autom. Lett., 2021

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System.
IEEE Robotics Autom. Lett., 2021

Model-Based Meta-Reinforcement Learning for Flight With Suspended Payloads.
IEEE Robotics Autom. Lett., 2021

How to train your robot with deep reinforcement learning: lessons we have learned.
Int. J. Robotics Res., 2021

AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale.
CoRR, 2021

Training on Test Data with Bayesian Adaptation for Covariate Shift.
CoRR, 2021

ReLMM: Practical RL for Learning Mobile Manipulation Skills Using Only Onboard Sensors.
CoRR, 2021

Persistent Reinforcement Learning via Subgoal Curricula.
CoRR, 2021

Explore and Control with Adversarial Surprise.
CoRR, 2021

Multi-Robot Deep Reinforcement Learning for Mobile Navigation.
CoRR, 2021

FitVid: Overfitting in Pixel-Level Video Prediction.
CoRR, 2021

Reinforcement Learning as One Big Sequence Modeling Problem.
CoRR, 2021

Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning.
CoRR, 2021

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale.
CoRR, 2021

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills.
CoRR, 2021

RECON: Rapid Exploration for Open-World Navigation with Latent Goal Models.
CoRR, 2021

How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned.
CoRR, 2021

Bayesian Adaptation for Covariate Shift.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Adaptive Risk Minimization: Learning to Adapt to Domain Shift.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

COMBO: Conservative Offline Model-Based Policy Optimization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Autonomous Reinforcement Learning via Subgoal Curricula.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Outcome-Driven Reinforcement Learning via Variational Inference.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Information is Power: Intrinsic Control via Information Capture.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Pragmatic Image Compression for Human-in-the-Loop Decision-Making.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Offline Reinforcement Learning as One Big Sequence Modeling Problem.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Robust Predictable Control.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

ViNG: Learning Open-World Navigation with Visual Goals.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

What Can I Do Here? Learning New Skills by Imagining Visual Affordances.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation.
Proceedings of the 38th International Conference on Machine Learning, 2021

Conservative Objective Models for Effective Offline Model-Based Optimization.
Proceedings of the 38th International Conference on Machine Learning, 2021

Model-Based Reinforcement Learning via Latent-Space Collocation.
Proceedings of the 38th International Conference on Machine Learning, 2021

Simple and Effective VAE Training with Calibrated Decoders.
Proceedings of the 38th International Conference on Machine Learning, 2021

Emergent Social Learning via Multi-agent Reinforcement Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

Offline Meta-Reinforcement Learning with Advantage Weighting.
Proceedings of the 38th International Conference on Machine Learning, 2021

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021


Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills.
Proceedings of the 38th International Conference on Machine Learning, 2021

Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment.
Proceedings of the 38th International Conference on Machine Learning, 2021

Model-Based Visual Planning with Self-Supervised Functional Distances.
Proceedings of the 9th International Conference on Learning Representations, 2021

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

Recurrent Independent Mechanisms.
Proceedings of the 9th International Conference on Learning Representations, 2021

Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments.
Proceedings of the 9th International Conference on Learning Representations, 2021

Learning to Reach Goals via Iterated Supervised Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback.
Proceedings of the 9th International Conference on Learning Representations, 2021

Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation.
Proceedings of the 9th International Conference on Learning Representations, 2021

Benchmarks for Deep Off-Policy Evaluation.
Proceedings of the 9th International Conference on Learning Representations, 2021

C-Learning: Learning to Achieve Goals via Recursive Classification.
Proceedings of the 9th International Conference on Learning Representations, 2021

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers.
Proceedings of the 9th International Conference on Learning Representations, 2021

Evolving Reinforcement Learning Algorithms.
Proceedings of the 9th International Conference on Learning Representations, 2021

Conservative Safety Critics for Exploration.
Proceedings of the 9th International Conference on Learning Representations, 2021

SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments.
Proceedings of the 9th International Conference on Learning Representations, 2021

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

Learning Invariant Representations for Reinforcement Learning without Reconstruction.
Proceedings of the 9th International Conference on Learning Representations, 2021

Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

Rapid Exploration for Open-World Navigation with Latent Goal Models.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

AW-Opt: Learning Robotic Skills with Imitation andReinforcement at Scale.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

Understanding the World Through Action.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

A Workflow for Offline Model-Free Robotic Reinforcement Learning.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

Scaling Up Multi-Task Robotic Reinforcement Learning.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

2020
Morphology-Agnostic Visual Robotic Control.
IEEE Robotics Autom. Lett., 2020

Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks.
IEEE Robotics Autom. Lett., 2020

Cognitive Mapping and Planning for Visual Navigation.
Int. J. Comput. Vis., 2020

Variable-Shot Adaptation for Online Meta-Learning.
CoRR, 2020

WILDS: A Benchmark of in-the-Wild Distribution Shifts.
CoRR, 2020

Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning.
CoRR, 2020

Amortized Conditional Normalized Maximum Likelihood.
CoRR, 2020

Rearrangement: A Challenge for Embodied AI.
CoRR, 2020

COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning.
CoRR, 2020

γ-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction.
CoRR, 2020

MELD: Meta-Reinforcement Learning from Images via Latent State Models.
CoRR, 2020

Multi-agent Social Reinforcement Learning Improves Generalization.
CoRR, 2020

Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift.
CoRR, 2020

Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems.
CoRR, 2020

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors.
CoRR, 2020

Ecological Reinforcement Learning.
CoRR, 2020

Accelerating Online Reinforcement Learning with Offline Datasets.
CoRR, 2020

Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling.
CoRR, 2020

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems.
CoRR, 2020

Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation.
CoRR, 2020

D4RL: Datasets for Deep Data-Driven Reinforcement Learning.
CoRR, 2020

Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting.
CoRR, 2020

AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos.
Proceedings of the Robotics: Science and Systems XVI, 2020

Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning.
Proceedings of the Robotics: Science and Systems XVI, 2020

Learning Agile Robotic Locomotion Skills by Imitating Animals.
Proceedings of the Robotics: Science and Systems XVI, 2020

MOPO: Model-based Offline Policy Optimization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Gradient Surgery for Multi-Task Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Continual Learning of Control Primitives : Skill Discovery via Reset-Games.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Conservative Q-Learning for Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Model Inversion Networks for Model-Based Optimization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020

Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020

Scaled Autonomy: Enabling Human Operators to Control Robot Fleets.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Scalable Multi-Task Imitation Learning with Autonomous Improvement.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

OmniTact: A Multi-Directional High-Resolution Touch Sensor.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

TRASS: Time Reversal as Self-Supervision.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings.
Proceedings of the 37th International Conference on Machine Learning, 2020

Learning Human Objectives by Evaluating Hypothetical Behavior.
Proceedings of the 37th International Conference on Machine Learning, 2020

Skew-Fit: State-Covering Self-Supervised Reinforcement Learning.
Proceedings of the 37th International Conference on Machine Learning, 2020

Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Proceedings of the 37th International Conference on Machine Learning, 2020

Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions.
Proceedings of the 37th International Conference on Machine Learning, 2020

The Ingredients of Real World Robotic Reinforcement Learning.
Proceedings of the 8th International Conference on Learning Representations, 2020

Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards.
Proceedings of the 8th International Conference on Learning Representations, 2020

Meta-Learning without Memorization.
Proceedings of the 8th International Conference on Learning Representations, 2020

Thinking While Moving: Deep Reinforcement Learning with Concurrent Control.
Proceedings of the 8th International Conference on Learning Representations, 2020

Dynamics-Aware Unsupervised Discovery of Skills.
Proceedings of the 8th International Conference on Learning Representations, 2020

Deep Imitative Models for Flexible Inference, Planning, and Control.
Proceedings of the 8th International Conference on Learning Representations, 2020

SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards.
Proceedings of the 8th International Conference on Learning Representations, 2020

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation.
Proceedings of the 8th International Conference on Learning Representations, 2020

Model Based Reinforcement Learning for Atari.
Proceedings of the 8th International Conference on Learning Representations, 2020

Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery.
Proceedings of the 8th International Conference on Learning Representations, 2020

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives.
Proceedings of the 8th International Conference on Learning Representations, 2020

The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget.
Proceedings of the 8th International Conference on Learning Representations, 2020

Adversarial Policies: Attacking Deep Reinforcement Learning.
Proceedings of the 8th International Conference on Learning Representations, 2020

Learning Predictive Models from Observation and Interaction.
Proceedings of the Computer Vision - ECCV 2020, 2020

RL-CycleGAN: Reinforcement Learning Aware Simulation-to-Real.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

MELD: Meta-Reinforcement Learning from Images via Latent State Models.
Proceedings of the 4th Conference on Robot Learning, 2020

Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting.
Proceedings of the 4th Conference on Robot Learning, 2020

Chaining Behaviors from Data with Model-Free Reinforcement Learning.
Proceedings of the 4th Conference on Robot Learning, 2020

Reinforcement Learning with Videos: Combining Offline Observations with Interaction.
Proceedings of the 4th Conference on Robot Learning, 2020

Assisted Perception: Optimizing Observations to Communicate State.
Proceedings of the 4th Conference on Robot Learning, 2020

Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning.
Proceedings of the 4th Conference on Robot Learning, 2020

Learning to Walk in the Real World with Minimal Human Effort.
Proceedings of the 4th Conference on Robot Learning, 2020

Unsupervised Reinforcement Learning.
Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, 2020

2019
Low-Level Control of a Quadrotor With Deep Model-Based Reinforcement Learning.
IEEE Robotics Autom. Lett., 2019

Reward-Conditioned Policies.
CoRR, 2019

Learning To Reach Goals Without Reinforcement Learning.
CoRR, 2019

SMiRL: Surprise Minimizing RL in Dynamic Environments.
CoRR, 2019

Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control.
CoRR, 2019

If MaxEnt RL is the Answer, What is the Question?
CoRR, 2019

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning.
CoRR, 2019

Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?
CoRR, 2019

Dynamical Distance Learning for Unsupervised and Semi-Supervised Skill Discovery.
CoRR, 2019

Efficient Exploration via State Marginal Matching.
CoRR, 2019

Learning Powerful Policies by Using Consistent Dynamics Model.
CoRR, 2019

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward.
CoRR, 2019

Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction.
CoRR, 2019

Extending Deep Model Predictive Control with Safety Augmented Value Estimation from Demonstrations.
CoRR, 2019

SQIL: Imitation Learning via Regularized Behavioral Cloning.
CoRR, 2019

REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning.
CoRR, 2019

End-to-End Robotic Reinforcement Learning without Reward Engineering.
CoRR, 2019

VideoFlow: A Flow-Based Generative Model for Video.
CoRR, 2019

Model-Based Reinforcement Learning for Atari.
CoRR, 2019

Artificial Intelligence for Prosthetics - challenge solutions.
CoRR, 2019

Improvisation through Physical Understanding: Using Novel Objects As Tools with Visual Foresight.
Proceedings of the Robotics: Science and Systems XV, 2019

End-To-End Robotic Reinforcement Learning without Reward Engineering.
Proceedings of the Robotics: Science and Systems XV, 2019

Learning to Walk Via Deep Reinforcement Learning.
Proceedings of the Robotics: Science and Systems XV, 2019

Meta-Learning with Implicit Gradients.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Wasserstein Dependency Measure for Representation Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Planning with Goal-Conditioned Policies.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Guided Meta-Policy Search.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

When to Trust Your Model: Model-Based Policy Optimization.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Unsupervised Curricula for Visual Meta-Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Off-Policy Evaluation via Off-Policy Classification.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Causal Confusion in Imitation Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Compositional Plan Vectors.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

One-Shot Composition of Vision-Based Skills from Demonstration.
Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost.
Proceedings of the International Conference on Robotics and Automation, 2019

REPLAB: A Reproducible Low-Cost Arm Benchmark for Robotic Learning.
Proceedings of the International Conference on Robotics and Automation, 2019

Manipulation by Feel: Touch-Based Control with Deep Predictive Models.
Proceedings of the International Conference on Robotics and Automation, 2019

Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty.
Proceedings of the International Conference on Robotics and Automation, 2019

Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matching.
Proceedings of the International Conference on Robotics and Automation, 2019

Data-efficient Learning of Morphology and Controller for a Microrobot.
Proceedings of the International Conference on Robotics and Automation, 2019

Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight.
Proceedings of the International Conference on Robotics and Automation, 2019

Residual Reinforcement Learning for Robot Control.
Proceedings of the International Conference on Robotics and Automation, 2019

SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019

Learning a Prior over Intent via Meta-Inverse Reinforcement Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables.
Proceedings of the 36th International Conference on Machine Learning, 2019

EMI: Exploration with Mutual Information.
Proceedings of the 36th International Conference on Machine Learning, 2019

Diagnosing Bottlenecks in Deep Q-learning Algorithms.
Proceedings of the 36th International Conference on Machine Learning, 2019

Online Meta-Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019

Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow.
Proceedings of the 7th International Conference on Learning Representations, 2019

Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL.
Proceedings of the 7th International Conference on Learning Representations, 2019

Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Near-Optimal Representation Learning for Hierarchical Reinforcement Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Time-Agnostic Prediction: Predicting Predictable Video Frames.
Proceedings of the 7th International Conference on Learning Representations, 2019

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Unsupervised Learning via Meta-Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

InfoBot: Transfer and Exploration via the Information Bottleneck.
Proceedings of the 7th International Conference on Learning Representations, 2019

Recall Traces: Backtracking Models for Efficient Reinforcement Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Learning Actionable Representations with Goal Conditioned Policies.
Proceedings of the 7th International Conference on Learning Representations, 2019

From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following.
Proceedings of the 7th International Conference on Learning Representations, 2019

Diversity is All You Need: Learning Skills without a Reward Function.
Proceedings of the 7th International Conference on Learning Representations, 2019

Guiding Policies with Language via Meta-Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Automatically Composing Representation Transformations as a Means for Generalization.
Proceedings of the 7th International Conference on Learning Representations, 2019

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

Entity Abstraction in Visual Model-Based Reinforcement Learning.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

Contextual Imagined Goals for Self-Supervised Robotic Learning.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

Deep Dynamics Models for Learning Dexterous Manipulation.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

Learning Latent Plans from Play.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

RoboNet: Large-Scale Multi-Robot Learning.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

2018
SFV: reinforcement learning of physical skills from videos.
ACM Trans. Graph., 2018

DeepMimic: example-guided deep reinforcement learning of physics-based character skills.
ACM Trans. Graph., 2018

Learning Flexible and Reusable Locomotion Primitives for a Microrobot.
IEEE Robotics Autom. Lett., 2018

More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch.
IEEE Robotics Autom. Lett., 2018

Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection.
Int. J. Robotics Res., 2018

Soft Actor-Critic Algorithms and Applications.
CoRR, 2018

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control.
CoRR, 2018

Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play.
CoRR, 2018

Guiding Policies with Language via Meta-Learning.
CoRR, 2018

One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks.
CoRR, 2018

EMI: Exploration with Mutual Information Maximizing State and Action Embeddings.
CoRR, 2018

Time Reversal as Self-Supervision.
CoRR, 2018

Addressing Sample Inefficiency and Reward Bias in Inverse Reinforcement Learning.
CoRR, 2018

SOLAR: Deep Structured Latent Representations for Model-Based Reinforcement Learning.
CoRR, 2018

QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation.
CoRR, 2018

Few-Shot Segmentation Propagation with Guided Networks.
CoRR, 2018

Unsupervised Meta-Learning for Reinforcement Learning.
CoRR, 2018

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review.
CoRR, 2018

Stochastic Adversarial Video Prediction.
CoRR, 2018

Universal Planning Networks.
CoRR, 2018

Recall Traces: Backtracking Models for Efficient Reinforcement Learning.
CoRR, 2018

Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments.
CoRR, 2018

Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning.
CoRR, 2018

Learning to Adapt: Meta-Learning for Model-Based Control.
CoRR, 2018

Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning.
CoRR, 2018

Shared Autonomy via Deep Reinforcement Learning.
Proceedings of the Robotics: Science and Systems XIV, 2018

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations.
Proceedings of the Robotics: Science and Systems XIV, 2018

Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Visual Reinforcement Learning with Imagined Goals.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Data-Efficient Hierarchical Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Visual Memory for Robust Path Following.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Meta-Reinforcement Learning of Structured Exploration Strategies.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Probabilistic Model-Agnostic Meta-Learning.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Learning with Latent Language.
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018

Learning Image-Conditioned Dynamics Models for Control of Underactuated Legged Millirobots.
Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018

Time-Contrastive Networks: Self-Supervised Learning from Video.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-to-End Learning from Demonstration.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Composable Deep Reinforcement Learning for Robotic Manipulation.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Deep Object-Centric Representations for Generalizable Robot Learning.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

The Mirage of Action-Dependent Baselines in Reinforcement Learning.
Proceedings of the 35th International Conference on Machine Learning, 2018

Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control.
Proceedings of the 35th International Conference on Machine Learning, 2018

Regret Minimization for Partially Observable Deep Reinforcement Learning.
Proceedings of the 35th International Conference on Machine Learning, 2018

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.
Proceedings of the 35th International Conference on Machine Learning, 2018

Latent Space Policies for Hierarchical Reinforcement Learning.
Proceedings of the 35th International Conference on Machine Learning, 2018

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings.
Proceedings of the 35th International Conference on Machine Learning, 2018

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning.
Proceedings of the 6th International Conference on Learning Representations, 2018

Conditional Networks for Few-Shot Semantic Segmentation.
Proceedings of the 6th International Conference on Learning Representations, 2018

Temporal Difference Models: Model-Free Deep RL for Model-Based Control.
Proceedings of the 6th International Conference on Learning Representations, 2018

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes.
Proceedings of the 6th International Conference on Learning Representations, 2018

Divide-and-Conquer Reinforcement Learning.
Proceedings of the 6th International Conference on Learning Representations, 2018

Reinforcement Learning from Imperfect Demonstrations.
Proceedings of the 6th International Conference on Learning Representations, 2018

Learning Robust Rewards with Adverserial Inverse Reinforcement Learning.
Proceedings of the 6th International Conference on Learning Representations, 2018

Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm.
Proceedings of the 6th International Conference on Learning Representations, 2018

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning.
Proceedings of the 6th International Conference on Learning Representations, 2018

Stochastic Variational Video Prediction.
Proceedings of the 6th International Conference on Learning Representations, 2018

Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Learning Instance Segmentation by Interaction.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

Few-Shot Goal Inference for Visuomotor Learning and Planning.
Proceedings of the 2nd Annual Conference on Robot Learning, 2018

Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation.
Proceedings of the 2nd Annual Conference on Robot Learning, 2018

Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation.
Proceedings of the 2nd Annual Conference on Robot Learning, 2018

Grasp2Vec: Learning Object Representations from Self-Supervised Grasping.
Proceedings of the 2nd Annual Conference on Robot Learning, 2018

Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning.
Proceedings of the 2nd Annual Conference on Robot Learning, 2018

2017
Unifying Map and Landmark Based Representations for Visual Navigation.
CoRR, 2017

Sim2Real View Invariant Visual Servoing by Recurrent Control.
CoRR, 2017

Neural Network Dynamics Models for Control of Under-actuated Legged Millirobots.
CoRR, 2017

Learning Robust Rewards with Adversarial Inverse Reinforcement Learning.
CoRR, 2017

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations.
CoRR, 2017

MBMF: Model-Based Priors for Model-Free Reinforcement Learning.
CoRR, 2017

Uncertainty-Aware Reinforcement Learning for Collision Avoidance.
CoRR, 2017

CAD2RL: Real Single-Image Flight Without a Single Real Image.
Proceedings of the Robotics: Science and Systems XIII, 2017

Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

EX2: Exploration with Exemplar Models for Deep Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Collective robot reinforcement learning with distributed asynchronous guided policy search.
Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017

Deep reinforcement learning for tensegrity robot locomotion.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Learning from the hindsight plan - Episodic MPC improvement.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Combining self-supervised learning and imitation for vision-based rope manipulation.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Reset-free guided policy search: Efficient deep reinforcement learning with stochastic initial states.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

PLATO: Policy learning using adaptive trajectory optimization.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Deep visual foresight for planning robot motion.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Learning modular neural network policies for multi-task and multi-robot transfer.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Path integral guided policy search.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Reinforcement Learning with Deep Energy-Based Policies.
Proceedings of the 34th International Conference on Machine Learning, 2017

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017

Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning.
Proceedings of the 34th International Conference on Machine Learning, 2017

Modular Multitask Reinforcement Learning with Policy Sketches.
Proceedings of the 34th International Conference on Machine Learning, 2017

Unsupervised Perceptual Rewards for Imitation Learning.
Proceedings of the 5th International Conference on Learning Representations, 2017

EPOpt: Learning Robust Neural Network Policies Using Model Ensembles.
Proceedings of the 5th International Conference on Learning Representations, 2017

Learning Visual Servoing with Deep Features and Fitted Q-Iteration.
Proceedings of the 5th International Conference on Learning Representations, 2017

Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic.
Proceedings of the 5th International Conference on Learning Representations, 2017

Generalizing Skills with Semi-Supervised Reinforcement Learning.
Proceedings of the 5th International Conference on Learning Representations, 2017

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning.
Proceedings of the 5th International Conference on Learning Representations, 2017

GPLAC: Generalizing Vision-Based Robotic Skills Using Weakly Labeled Images.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Time-Contrastive Networks: Self-Supervised Learning from Multi-view Observation.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017

Cognitive Mapping and Planning for Visual Navigation.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Learning Robotic Manipulation of Granular Media.
Proceedings of the 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, 2017

End-to-End Learning of Semantic Grasping.
Proceedings of the 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, 2017

One-Shot Visual Imitation Learning via Meta-Learning.
Proceedings of the 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, 2017

Self-Supervised Visual Planning with Temporal Skip Connections.
Proceedings of the 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, 2017

The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
Proceedings of the 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, 2017

Goal-driven dynamics learning via Bayesian optimization.
Proceedings of the 56th IEEE Annual Conference on Decision and Control, 2017

2016
End-to-End Training of Deep Visuomotor Policies.
J. Mach. Learn. Res., 2016

Value Iteration Networks.
CoRR, 2016

High-Dimensional Continuous Control Using Generalized Advantage Estimation.
Proceedings of the 4th International Conference on Learning Representations, 2016

(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image.
CoRR, 2016

Guided Policy Search as Approximate Mirror Descent.
CoRR, 2016

Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection.
CoRR, 2016

Learning Dexterous Manipulation Policies from Experience and Imitation.
CoRR, 2016

Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration.
CoRR, 2016

MuProp: Unbiased Backpropagation for Stochastic Neural Networks.
Proceedings of the 4th International Conference on Learning Representations, 2016

Deep Reinforcement Learning for Robotic Manipulation.
CoRR, 2016

Learning Visual Predictive Models of Physics for Playing Billiards.
Proceedings of the 4th International Conference on Learning Representations, 2016

A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models.
CoRR, 2016

Learning to Poke by Poking: Experiential Learning of Intuitive Physics.
CoRR, 2016

Adapting Deep Visuomotor Representations with Weak Pairwise Constraints.
Proceedings of the Algorithmic Foundations of Robotics XII, 2016

Value Iteration Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Guided Policy Search via Approximate Mirror Descent.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Backprop KF: Learning Discriminative Deterministic State Estimators.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Unsupervised Learning for Physical Interaction through Video Prediction.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Learning Hand-Eye Coordination for Robotic Grasping with Large-Scale Data Collection.
Proceedings of the International Symposium on Experimental Robotics, 2016

Learning dexterous manipulation for a soft robotic hand from human demonstrations.
Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016

One-shot learning of manipulation skills with online dynamics adaptation and neural network priors.
Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016

Learning deep neural network policies with continuous memory states.
Proceedings of the 2016 IEEE International Conference on Robotics and Automation, 2016

Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search.
Proceedings of the 2016 IEEE International Conference on Robotics and Automation, 2016

Model-based reinforcement learning with parametrized physical models and optimism-driven exploration.
Proceedings of the 2016 IEEE International Conference on Robotics and Automation, 2016

Optimal control with learned local models: Application to dexterous manipulation.
Proceedings of the 2016 IEEE International Conference on Robotics and Automation, 2016

Deep spatial autoencoders for visuomotor learning.
Proceedings of the 2016 IEEE International Conference on Robotics and Automation, 2016

Continuous Deep Q-Learning with Model-based Acceleration.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization.
Proceedings of the 33nd International Conference on Machine Learning, 2016

2015
Policy Learning with Continuous Memory States for Partially Observed Robotic Control.
CoRR, 2015

Towards Adapting Deep Visuomotor Representations from Simulated to Real Environments.
CoRR, 2015

Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models.
CoRR, 2015

Recurrent Network Models for Kinematic Tracking.
CoRR, 2015

Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders.
CoRR, 2015

Learning from multiple demonstrations using trajectory-aware non-rigid registration with applications to deformable object manipulation.
Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2015

Learning compound multi-step controllers under unknown dynamics.
Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2015

Optimism-driven exploration for nonlinear systems.
Proceedings of the IEEE International Conference on Robotics and Automation, 2015

Learning contact-rich manipulation skills with guided policy search.
Proceedings of the IEEE International Conference on Robotics and Automation, 2015

Learning force-based manipulation of deformable objects from multiple demonstrations.
Proceedings of the IEEE International Conference on Robotics and Automation, 2015

Trust Region Policy Optimization.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Recurrent Network Models for Human Dynamics.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

2014
Motor skill learning with local trajectory methods.
PhD thesis, 2014

Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Learning Complex Neural Network Policies with Trajectory Optimization.
Proceedings of the 31th International Conference on Machine Learning, 2014

Offline policy evaluation across representations with applications to educational games.
Proceedings of the International conference on Autonomous Agents and Multi-Agent Systems, 2014

2013
Exploring Deep and Recurrent Architectures for Optimal Control.
CoRR, 2013

Variational Policy Search via Trajectory Optimization.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Guided Policy Search.
Proceedings of the 30th International Conference on Machine Learning, 2013

2012
Continuous character control with low-dimensional embeddings.
ACM Trans. Graph., 2012

Physically Plausible Simulation for Character Animation.
Proceedings of the 2012 Eurographics/ACM SIGGRAPH Symposium on Computer Animation, 2012

Continuous Inverse Optimal Control with Locally Optimal Examples.
Proceedings of the 29th International Conference on Machine Learning, 2012

2011
Space-time planning with parameterized locomotion controllers.
ACM Trans. Graph., 2011

Nonlinear Inverse Reinforcement Learning with Gaussian Processes.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

2010
Gesture controllers.
ACM Trans. Graph., 2010

Feature Construction for Inverse Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

2009
Real-time prosody-driven synthesis of body language.
ACM Trans. Graph., 2009


  Loading...