Preprints
VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation
arXiv preprint, 2025, Runners-up for Madrona Prize at UW, Oral at Workshop on Generalist Robot Policies in the Wild
Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
arXiv preprint, 2025
PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies
arXiv preprint, 2025
Accelerating online reinforcement learning with offline datasets
arXiv preprint, 2020
Unsupervised meta-learning for reinforcement learning
arXiv preprint, 2018, best paper at LLARLA workshop at ICML 2018
2025
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
Conference on Robot Learning (CoRL), 2025 (Oral, Best Paper Nominee)
RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
Conference on Robot Learning (CoRL), 2025 (Oral)
ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning
Conference on Robot Learning (CoRL), 2025
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Robotics: Science and Systems (RSS), 2025 (Best Paper Award), Best Paper at ICML 2025 Workshop on Building Physically Plausible World Models
DRAWER: Digital Reconstruction and Articulation With Environment Realism
Conference on Computer Vision and Pattern Recognition (CVPR), 2025
DUOLINGO: Dynamics Utilization for Online Translation of Actions
International Conference on Robotics and Automation (ICRA), 2025
SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks
International Conference on Learning Representations (ICLR), 2025 (Spotlight)
HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation
International Conference on Learning Representations (ICLR), 2025
Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning
International Conference on Learning Representations (ICLR), 2025
STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
International Conference on Learning Representations (ICLR), 2025
2024
Learning to Cooperate with Humans using Generative Agents
Neural Information Processing Systems (NeurIPS), 2024
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
Neural Information Processing Systems (NeurIPS), 2024
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)
Distributional Successor Features Enable Zero-Shot Policy Optimization
Neural Information Processing Systems (NeurIPS), 2024
Teaching Robots with Show and Tell: Using Foundation Models to Synthesize Robot Policies from Language and Visual Demonstration
Conference on Robot Learning (CoRL), 2024
Semantically Controllable Augmentations for Generalizable Robot Learning
International Journal of Robotics Research (IJRR), 2024
Data Efficient Behavior Cloning for Fine Manipulation via Continuity-based Corrective Labels
International Conference on Intelligent Robots and Systems (IROS), 2024
DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset
Robotics: Science and Systems (RSS), 2024
Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
Robotics: Science and Systems (RSS), 2024
URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images
Robotics: Science and Systems (RSS), 2024
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
International Conference on Robotics and Automation (ICRA), 2024
Rank2Reward: Learning Shaped Reward Functions from Passive Video
International Conference on Robotics and Automation (ICRA), 2024
Learning to Grasp in Clutter with Interactive Visual Failure Prediction
International Conference on Robotics and Automation (ICRA), 2024
Lifelong Robot Learning with Human Assisted Language Planners
International Conference on Robotics and Automation (ICRA), 2024
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
International Conference on Robotics and Automation (ICRA), 2024 (Finalist for Best Paper Award in Robot Vision)
ASID: Active Exploration for System Identification and Reconstruction in Robotic Manipulation
International Conference on Learning Representations (ICLR), 2024
Modeling Boundedly Rational Agents with Latent Inference Budgets
International Conference on Learning Representations (ICLR), 2024
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
International Conference on Learning Representations (ICLR), 2024
CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning
International Conference on Learning Representations (ICLR), 2024
2023
RoboHive: A Unified Framework for Robot Learning
Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2023
Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback
Conference on Robot Learning (CoRL), 2023
REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation
Conference on Robot Learning (CoRL), 2023
Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching
Conference on Robot Learning (CoRL), 2023
Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
Neural Information Processing Systems (NeurIPS), 2023
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets
Neural Information Processing Systems (NeurIPS), 2023
Self-Supervised Reinforcement Learning that Transfers using Random Features
Neural Information Processing Systems (NeurIPS), 2023
RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability
Neural Information Processing Systems (NeurIPS), 2023 (Spotlight)
Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective
Conference on Learning Theory (COLT), 2023
Guiding Pretraining in Reinforcement Learning with Large Language Models
International Conference on Machine Learning (ICML), 2023
GenAug: Retargeting behaviors to unseen situations via Generative Augmentation
Robotics: Science and Systems (RSS), 2023 (Best Systems Paper Finalist)
Learning to Extrapolate: A Transductive Approach
International Conference on Learning Representations (ICLR), 2023
TactoFind: A Tactile Only System for Object Retrieval
International Conference on Robotics and Automation (ICRA), 2023
Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning
International Conference on Robotics and Automation (ICRA), 2023
Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance
International Conference on Robotics and Automation (ICRA), 2023
2022
Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation
Conference on Robot Learning (CoRL), 2022
Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
Neural Information Processing Systems (NeurIPS), 2022
Distributionally Adaptive Meta Reinforcement Learning
Neural Information Processing Systems (NeurIPS), 2022
Autonomous Reinforcement Learning: Formalism and Benchmarking
International Conference on Learning Representations (ICLR), 2022
2021
Teachable Reinforcement Learning via Advice Distillation
Neural Information Processing Systems (NeurIPS), 2021
Persistent Reinforcement Learning via Subgoal Curricula
Neural Information Processing Systems (NeurIPS), 2021
Adaptive risk minimization: A meta-learning approach for tackling group shift
Neural Information Processing Systems (NeurIPS), 2021
Which Mutual-Information Representation Learning Objectives are Sufficient for Control?
Neural Information Processing Systems (NeurIPS), 2021
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
International Conference on Machine Learning (ICML), 2021
Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention
International Conference on Robotics and Automation (ICRA), 2021
Fully Autonomous Real-World Reinforcement Learning for Mobile Manipulation
Conference on Robot Learning (CoRL), 2021
Learning to reach goals via iterated supervised learning
International Conference on Learning Representations (ICLR), 2021 (Oral)
2020
The ingredients of real-world robotic reinforcement learning
International Conference on Learning Representations (ICLR), 2020 (spotlight)
Discor: Corrective feedback in reinforcement learning via distribution correction
Neural Information Processing Systems (NeurIPS), 2020 (spotlight)
Gradient surgery for multi-task learning
Neural Information Processing Systems (NeurIPS), 2020
2019
Unsupervised curricula for visual meta-reinforcement learning
Neural Information Processing Systems (NeurIPS), 2019 (spotlight)
ROBEL: RObotics BEnchmarks for Learning with low-cost robots
Conference on Robot Learning (CoRL), 2019
Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning
Conference on Robot Learning (CoRL), 2019
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost
International Conference on Robotics and Automation (ICRA), 2019
Diversity is all you need: Learning skills without a reward function
International Conference on Learning Representations (ICLR), 2019
Guiding policies with language via meta-learning
International Conference on Learning Representations (ICLR), 2019
Learning actionable representations with goal-conditioned policies
International Conference on Learning Representations (ICLR), 2019
Automatically composing representation transformations as a means for generalization
International Conference on Learning Representations (ICLR), 2019
2018
Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory embeddings
International Conference on Machine Learning (ICML), 2018
Imitation from observation: Learning to imitate behaviors from raw video via context translation
International Conference on Robotics and Automation (ICRA), 2018
Meta-reinforcement learning of structured exploration strategies
Neural Information Processing Systems (NeurIPS), 2018 (spotlight)
Learning complex dexterous manipulation with deep reinforcement learning and demonstrations
Robotics Science and Systems (RSS), 2018
2017
Learning modular neural network policies for multi-task and multi-robot transfer
International Conference on Robotics and Automation (ICRA), 2017
Learning invariant feature spaces to transfer skills with reinforcement learning
International Conference on Learning Representations (ICLR), 2017
2016
Learning dexterous manipulation for a soft robotic hand from human demonstrations
International Conference on Intelligent Robots and Systems (IROS), 2016
Guided search for task and motion plans using learned heuristics
International Conference on Robotics and Automation (ICRA), 2016
2015
Learning from multiple demonstrations using trajectory-aware non-rigid registration with applications to deformable object manipulation
International Conference on Intelligent Robots and Systems (IROS), 2015
Learning force-based manipulation of deformable objects from multiple demonstrations
International Conference on Robotics and Automation (ICRA), 2015