Pulkit Agrawal

Orcid: 0000-0002-9569-6690

Affiliations:

Massachusetts Institute of Technology, Cambridge, MA, USA
University of California Berkeley, CA, USA (PhD 2018)

According to our database¹, Pulkit Agrawal authored at least 106 papers between 2011 and 2024.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2024

Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2024

Rapid locomotion via reinforcement learning.

[BibT_eX]

[DOI]

Int. J. Robotics Res., 2024

Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck.

[BibT_eX]

[DOI]

CoRR, 2024

ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning.

[BibT_eX]

[DOI]

CoRR, 2024

ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization.

[BibT_eX]

[DOI]

CoRR, 2024

Diffusion Policy Policy Optimization.

[BibT_eX]

[DOI]

CoRR, 2024

EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation.

[BibT_eX]

[DOI]

CoRR, 2024

From Imitation to Refinement - Residual RL for Precise Visual Assembly.

[BibT_eX]

[DOI]

CoRR, 2024

Automatic Environment Shaping is the Next Frontier in RL.

[BibT_eX]

[DOI]

Younghyo Park

Gabriel B. Margolis

Pulkit Agrawal

CoRR, 2024

Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation.

[BibT_eX]

[DOI]

CoRR, 2024

Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient.

[BibT_eX]

[DOI]

CoRR, 2024

Value Augmented Sampling for Language Model Alignment and Personalization.

[BibT_eX]

[DOI]

CoRR, 2024

JUICER: Data-Efficient Imitation Learning for Robotic Assembly.

[BibT_eX]

[DOI]

CoRR, 2024

Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation.

[BibT_eX]

[DOI]

CoRR, 2024

Training Neural Networks from Scratch with Parallel Low-Rank Adapters.

[BibT_eX]

[DOI]

CoRR, 2024

ROER: Regularized Optimal Experience Replay.

[BibT_eX]

RLJ, 2024

Rank2Reward: Learning Shaped Reward Functions from Passive Video.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Learning Force Control for Legged Manipulation.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Lifelong Robot Learning with Human Assisted Language Planners.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Everyday finger: a robotic finger that meets the needs of everyday interactive manipulation.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Maximizing Quadruped Velocity by Minimizing Energy.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Position: Automatic Environment Shaping is the Next Frontier in RL.

[BibT_eX]

[DOI]

Younghyo Park

Gabriel B. Margolis

Pulkit Agrawal

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

Random Latent Exploration for Deep Reinforcement Learning.

[BibT_eX]

[DOI]

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

Curiosity-driven Red-teaming for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Aligning Human and Robot Representations.

[BibT_eX]

[DOI]

Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 2024

OpenEQA: Embodied Question Answering in the Era of Foundation Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Visual dexterity: In-hand reorientation of novel and complex object shapes.

[BibT_eX]

[DOI]

Sci. Robotics, November, 2023

The Low-Rank Simplicity Bias in Deep Networks.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity.

[BibT_eX]

[DOI]

CoRR, 2023

Human-Assisted Continual Robot Learning with Foundation Models.

[BibT_eX]

[DOI]

CoRR, 2023

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback.

[BibT_eX]

[DOI]

CoRR, 2023

Neuro-Inspired Efficient Map Building via Fragmentation and Recall.

[BibT_eX]

[DOI]

CoRR, 2023

Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement.

[BibT_eX]

[DOI]

CoRR, 2023

Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies.

[BibT_eX]

[DOI]

Ligong Han

Seungwook Han

Shivchander Sudalairaj

CoRR, 2023

Geometry of contact: contact planning for multi-legged robots via spin models duality.

[BibT_eX]

[DOI]

CoRR, 2023

Aligning Robot and Human Representations.

[BibT_eX]

[DOI]

CoRR, 2023

Breadcrumbs to the Goal: Supervised Goal Selection from Human-in-the-Loop Feedback.

[BibT_eX]

[DOI]

Marcel Torne Villasevil

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

Human-Guided Complexity-Controlled Abstractions.

[BibT_eX]

[DOI]

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

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets.

[BibT_eX]

[DOI]

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

Compositional Foundation Models for Hierarchical Planning.

[BibT_eX]

[DOI]

Leslie Pack Kaelbling

Akash Srivastava

Pulkit Agrawal

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

Self-Supervised Reinforcement Learning that Transfers using Random Features.

[BibT_eX]

[DOI]

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

Visual Pre-Training for Navigation: What Can We Learn from Noise?

[BibT_eX]

[DOI]

Yanwei Wang

Ching-Yun Ko

Pulkit Agrawal

IROS, 2023

TactoFind: A Tactile Only System for Object Retrieval.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2023

DribbleBot: Dynamic Legged Manipulation in the Wild.

[BibT_eX]

[DOI]

Yandong Ji

Gabriel B. Margolis

Pulkit Agrawal

Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Statistical Learning under Heterogenous Distribution Shift.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

TGRL: An Algorithm for Teacher Guided Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Learning to Extrapolate: A Transductive Approach.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting.

[BibT_eX]

[DOI]

Zhang-Wei Hong

Pulkit Agrawal

Remi Tachet des Combes

Romain Laroche

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Is Conditional Generative Modeling all you need for Decision Making?

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement.

[BibT_eX]

[DOI]

Alberto Rodriguez Garcia

Pulkit Agrawal

Dieter Fox

Proceedings of the Conference on Robot Learning, 2023

Learning to See Physical Properties with Active Sensing Motor Policies.

[BibT_eX]

[DOI]

Proceedings of the Conference on Robot Learning, 2023

Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback.

[BibT_eX]

[DOI]

Max Balsells

Marcel Torne Villasevil

Proceedings of the Conference on Robot Learning, 2023

2022

Visual Dexterity: In-hand Dexterous Manipulation from Depth.

[BibT_eX]

[DOI]

CoRR, 2022

SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields.

[BibT_eX]

[DOI]

Leslie Pack Kaelbling

Tomás Lozano-Pérez

Pulkit Agrawal

CoRR, 2022

Bilinear value networks.

[BibT_eX]

[DOI]

Zhang-Wei Hong

Ge Yang

Pulkit Agrawal

CoRR, 2022

Redeeming intrinsic rewards via constrained optimization.

[BibT_eX]

[DOI]

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

Distributionally Adaptive Meta Reinforcement Learning.

[BibT_eX]

[DOI]

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

Stubborn: A Strong Baseline for Indoor Object Navigation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators.

[BibT_eX]

[DOI]

Proceedings of the 2022 International Conference on Robotics and Automation, 2022

Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation.

[BibT_eX]

[DOI]

Proceedings of the 2022 International Conference on Robotics and Automation, 2022

Stable Object Reorientation using Contact Plane Registration.

[BibT_eX]

[DOI]

Proceedings of the 2022 International Conference on Robotics and Automation, 2022

Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Offline RL Policies Should Be Trained to be Adaptive.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Overcoming The Spectral Bias of Neural Value Approximation.

[BibT_eX]

[DOI]

Ge Yang

Anurag Ajay

Pulkit Agrawal

Proceedings of the Tenth International Conference on Learning Representations, 2022

Bi-linear Value Networks for Multi-goal Reinforcement Learning.

[BibT_eX]

[DOI]

Zhang-Wei Hong

Ge Yang

Pulkit Agrawal

Proceedings of the Tenth International Conference on Learning Representations, 2022

Topological Experience Replay.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields.

[BibT_eX]

[DOI]

Anthony Simeonov

Yilun Du

Yen-Chen Lin

Alberto Rodriguez Garcia

Leslie Pack Kaelbling

Tomás Lozano-Pérez

Pulkit Agrawal

Proceedings of the Conference on Robot Learning, 2022

Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior.

[BibT_eX]

[DOI]

Gabriel B. Margolis

Pulkit Agrawal

Proceedings of the Conference on Robot Learning, 2022

Efficient Tactile Simulation with Differentiability for Robotic Manipulation.

[BibT_eX]

[DOI]

Jie Xu

Sangwoon Kim

Tao Chen

Alberto Rodriguez Garcia

Pulkit Agrawal

Wojciech Matusik

Shinjiro Sueda

Proceedings of the Conference on Robot Learning, 2022

2021

Equivariant Contrastive Learning.

[BibT_eX]

[DOI]

CoRR, 2021

An End-to-End Differentiable Framework for Contact-Aware Robot Design.

[BibT_eX]

[DOI]

Proceedings of the Robotics: Science and Systems XVII, Virtual Event, July 12-16, 2021., 2021

Residual Model Learning for Microrobot Control.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2021

Learning Task Informed Abstractions.

[BibT_eX]

[DOI]

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

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Learning to Jump from Pixels.

[BibT_eX]

[DOI]

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

3D Neural Scene Representations for Visuomotor Control.

[BibT_eX]

[DOI]

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

A System for General In-Hand Object Re-Orientation.

[BibT_eX]

[DOI]

Tao Chen

Jie Xu

Pulkit Agrawal

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

The Task Specification Problem.

[BibT_eX]

[DOI]

Pulkit Agrawal

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

Adapting Deep Learning Models to New Meteorological Contexts Using Transfer Learning.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021

2020

Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects.

[BibT_eX]

[DOI]

Anthony Simeonov

Yilun Du

Beomjoon Kim

Francois Robert Hogan

Joshua B. Tenenbaum

Pulkit Agrawal

Alberto Rodriguez

Proceedings of the 4th Conference on Robot Learning, 2020

Exploring Exploration: Comparing Children with Agents in Unified Exploration Environments.

[BibT_eX]

[DOI]

Proceedings of the 42th Annual Meeting of the Cognitive Science Society, 2020

2019

Superposition of many models into one.

[BibT_eX]

[DOI]

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

Curiouser and Curiouser: Children's intrinsic exploration of mazes and its effects on reaching a goal.

[BibT_eX]

[DOI]

Proceedings of the 41th Annual Meeting of the Cognitive Science Society, 2019

Human-level but not human-like: Deep Reinforcement Learning in the dark.

[BibT_eX]

[DOI]

Proceedings of the 41th Annual Meeting of the Cognitive Science Society, 2019

2018

Computational Sensorimotor Learning.

[BibT_eX]

[DOI]

Pulkit Agrawal

PhD thesis, 2018

Investigating Human Priors for Playing Video Games.

[BibT_eX]

[DOI]

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

Learning Instance Segmentation by Interaction.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

Zero-Shot Visual Imitation.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

2017

Combining self-supervised learning and imitation for vision-based rope manipulation.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Curiosity-driven Exploration by Self-supervised Prediction.

[BibT_eX]

[DOI]

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

Learning to Perform Physics Experiments via Deep Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 5th International Conference on Learning Representations, 2017

What will Happen Next? Forecasting Player Moves in Sports Videos.

[BibT_eX]

[DOI]

Panna Felsen

Pulkit Agrawal

Jitendra Malik

Proceedings of the IEEE International Conference on Computer Vision, 2017

2016

What makes ImageNet good for transfer learning?

[BibT_eX]

[DOI]

Mi-Young Huh

Pulkit Agrawal

Alexei A. Efros

CoRR, 2016

Learning Visual Predictive Models of Physics for Playing Billiards.

[BibT_eX]

[DOI]

Proceedings of the 4th International Conference on Learning Representations, 2016

Learning to Poke by Poking: Experiential Learning of Intuitive Physics.

[BibT_eX]

[DOI]

CoRR, 2016

Generic 3D Representation via Pose Estimation and Matching.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2016, 2016

Human Pose Estimation with Iterative Error Feedback.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

2015

Learning to See by Moving.

[BibT_eX]

[DOI]

Pulkit Agrawal

João Carreira

Jitendra Malik

Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

2014

Pixels to Voxels: Modeling Visual Representation in the Human Brain.

[BibT_eX]

[DOI]

CoRR, 2014

Analyzing the Performance of Multilayer Neural Networks for Object Recognition.

[BibT_eX]

[DOI]

Pulkit Agrawal

Ross B. Girshick

Jitendra Malik

Proceedings of the Computer Vision - ECCV 2014, 2014

2011

The automatic assessment of knowledge integration processes in project teams.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Computer Supported Collaborative Learning, 2011

Pulkit Agrawal

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...