Wen Sun

CoRR, 2024

Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization.

[BibT_eX]

[DOI]

CoRR, 2024

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics.

[BibT_eX]

[DOI]

CoRR, 2024

Understanding Preference Fine-Tuning Through the Lens of Coverage.

[BibT_eX]

[DOI]

CoRR, 2024

REBEL: Reinforcement Learning via Regressing Relative Rewards.

[BibT_eX]

[DOI]

CoRR, 2024

Dataset Reset Policy Optimization for RLHF.

[BibT_eX]

[DOI]

CoRR, 2024

RL for Consistency Models: Faster Reward Guided Text-to-Image Generation.

[BibT_eX]

[DOI]

CoRR, 2024

Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes.

[BibT_eX]

[DOI]

CoRR, 2024

Risk-Sensitive RL with Optimized Certainty Equivalents via Reduction to Standard RL.

[BibT_eX]

[DOI]

CoRR, 2024

JoinGym: An Efficient Join Order Selection Environment.

[BibT_eX]

RLJ, 2024

RL for Consistency Models: Reward Guided Text-to-Image Generation with Fast Inference.

[BibT_eX]

RLJ, 2024

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Provable Offline Preference-Based Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Provable Reward-Agnostic Preference-Based Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Making RL with Preference-based Feedback Efficient via Randomization.

[BibT_eX]

[DOI]

Runzhe Wu

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Adversarial Imitation Learning via Boosting.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Provably Efficient CVaR RL in Low-rank MDPs.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Contextual Bandits and Imitation Learning via Preference-Based Active Queries.

[BibT_eX]

[DOI]

CoRR, 2023

JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Learning to Generate Better Than Your LLM.

[BibT_eX]

[DOI]

CoRR, 2023

How to Query Human Feedback Efficiently in RL?

[BibT_eX]

[DOI]

CoRR, 2023

Provable Offline Reinforcement Learning with Human Feedback.

[BibT_eX]

[DOI]

CoRR, 2023

Refined Value-Based Offline RL under Realizability and Partial Coverage.

[BibT_eX]

[DOI]

CoRR, 2023

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Selective Sampling and Imitation Learning via Online Regression.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Contextual Bandits and Imitation Learning with Preference-Based Active Queries.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Distributional Offline Policy Evaluation with Predictive Error Guarantees.

[BibT_eX]

[DOI]

Runzhe Wu

Proceedings of the International Conference on Machine Learning, 2023

Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR.

[BibT_eX]

[DOI]

Kaiwen Wang

Nathan Kallus

Proceedings of the International Conference on Machine Learning, 2023

Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

PAC Reinforcement Learning for Predictive State Representations.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Hybrid RL: Using both offline and online data can make RL efficient.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Provable Benefits of Representational Transfer in Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

On the Effectiveness of Iterative Learning Control.

[BibT_eX]

[DOI]

Proceedings of the Learning for Dynamics and Control Conference, 2022

Online No-regret Model-Based Meta RL for Personalized Navigation.

[BibT_eX]

[DOI]

Proceedings of the Learning for Dynamics and Control Conference, 2022

Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Learning Bellman Complete Representations for Offline Policy Evaluation.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Representation Learning for Online and Offline RL in Low-rank MDPs.

[BibT_eX]

[DOI]

Xuezhou Zhang

Proceedings of the Tenth International Conference on Learning Representations, 2022

Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Corruption-robust Offline Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Pessimistic Model-based Offline RL: PAC Bounds and Posterior Sampling under Partial Coverage.

[BibT_eX]

[DOI]

CoRR, 2021

Corruption-Robust Offline Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage.

[BibT_eX]

[DOI]

CoRR, 2021

Optimism is All You Need: Model-Based Imitation Learning From Observation Alone.

[BibT_eX]

[DOI]

Rahul Kidambi

Jonathan D. Chang

CoRR, 2021

Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency.

[BibT_eX]

[DOI]

CoRR, 2021

Imitation Learning as f-Divergence Minimization.

[BibT_eX]

[DOI]

Siddhartha S. Srinivasa

Proceedings of the Algorithmic Foundations of Robotics XIV, 2021

MobILE: Model-Based Imitation Learning From Observation Alone.

[BibT_eX]

[DOI]

Rahul Kidambi

Jonathan D. Chang

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

Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage.

[BibT_eX]

[DOI]

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

Robust Policy Gradient against Strong Data Corruption.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Fairness of Exposure in Stochastic Bandits.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration.

[BibT_eX]

[DOI]

Yuda Song

Proceedings of the 38th International Conference on Machine Learning, 2021

Bilinear Classes: A Structural Framework for Provable Generalization in RL.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Corruption-robust exploration in episodic reinforcement learning.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

2020

Exploration in Action Space.

[BibT_eX]

[DOI]

Anirudh Vemula

CoRR, 2020

Learning the Linear Quadratic Regulator from Nonlinear Observations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Information Theoretic Regret Bounds for Online Nonlinear Control.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Constrained episodic reinforcement learning in concave-convex and knapsack settings.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Provably Efficient Model-based Policy Adaptation.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Disagreement-Regularized Imitation Learning.

[BibT_eX]

[DOI]

Kianté Brantley

Mikael Henaff

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Towards Generalization and Efficiency in Reinforcement Learning.

[BibT_eX]

[DOI]

PhD thesis, 2019

Policy Poisoning in Batch Reinforcement Learning and Control.

[BibT_eX]

[DOI]

CoRR, 2019

Policy Poisoning in Batch Reinforcement Learning and Control.

[BibT_eX]

[DOI]

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

Contextual Memory Trees.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Provably Efficient Imitation Learning from Observation Alone.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2019

Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective.

[BibT_eX]

[DOI]

Anirudh Vemula

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Model-Based Reinforcement Learning in Contextual Decision Processes.

[BibT_eX]

[DOI]

CoRR, 2018

Dual Policy Iteration.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Recurrent Predictive State Policy Networks.

[BibT_eX]

[DOI]

Ahmed Hefny

Zita Marinho

Siddhartha S. Srinivasa

Geoffrey J. Gordon

Proceedings of the 35th International Conference on Machine Learning, 2018

Truncated horizon Policy Search: Combining Reinforcement Learning & Imitation Learning.

[BibT_eX]

[DOI]

Byron Boots

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Predictive-State Decoders: Encoding the Future into Recurrent Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

Gradient Boosting on Stochastic Data Streams.

[BibT_eX]

[DOI]

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

Stochastic Extended LQR for Optimization-Based Motion Planning Under Uncertainty.

[BibT_eX]

[DOI]

Jur van den Berg

Ron Alterovitz

IEEE Trans Autom. Sci. Eng., 2016

Learning to Smooth with Bidirectional Predictive State Inference Machines.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016

Inference Machines for Nonparametric Filter Learning.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

Online Bellman Residual and Temporal Difference Algorithms with Predictive Error Guarantees.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

Learning to Filter with Predictive State Inference Machines.

[BibT_eX]

[DOI]

Proceedings of the 33nd International Conference on Machine Learning, 2016

Online Instrumental Variable Regression with Applications to Online Linear System Identification.

[BibT_eX]

[DOI]

Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

2015

High-Frequency Replanning Under Uncertainty Using Parallel Sampling-Based Motion Planning.

[BibT_eX]

[DOI]

Sachin Patil

Ron Alterovitz

IEEE Trans. Robotics, 2015

Online Bellman Residual Algorithms with Predictive Error Guarantees.

[BibT_eX]

[DOI]

Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

2014

Motion planning under uncertainty for medical needle steering using optimization in belief space.

[BibT_eX]

[DOI]