作者
Sergey Levine
Robotics / Reinforcement Learning
INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL
Comments Published in International Conference on Learning Representations (ICLR 2022)
CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning
When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?
Comments ICLR 2022. First two authors contributed equally
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Comments Accepted to ICLR 2022
Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning
Comments Interactive website at https://dbap-rl.github.io/
X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback
Comments Accepted to International Conference on Learning Representations (ICLR) 2021
Fully Online Meta-Learning Without Task Boundaries
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning
Comments Accepted to IEEE Conference on Robotics and Automation (ICRA) 2022
BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning
Comments CoRL 2021, 23 pages
Journal ref Conference on Robot Learning (pp. 991-1002). 2022 Jan 11
Data-Driven Offline Optimization For Architecting Hardware Accelerators
Comments First two authors contributed equally; published at ICLR 2022
COMBO: Conservative Offline Model-Based Policy Optimization
Comments NeurIPS 2021
Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification
Comments NeurIPS 2021 (oral). Website with code, videos, and blog post: https://ben-eysenbach.github.io/rce
Explore and Control with Adversarial Surprise
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization
CoMPS: Continual Meta Policy Search
Comments 23 pages, under review
Information is Power: Intrinsic Control via Information Capture
Comments NeurIPS 2021
Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
Comments 16 pages, Published at CoRL 2021
Adaptive Risk Minimization: Learning to Adapt to Domain Shift
Comments NeurIPS 2021 ; Project website: https://sites.google.com/view/adaptive-risk-minimization ; Code: https://github.com/henrikmarklund/arm
Offline Reinforcement Learning as One Big Sequence Modeling Problem
Comments NeurIPS 2021 (spotlight). Project page and code at: https://trajectory-transformer.github.io/
Generative Temporal Difference Learning for Infinite-Horizon Prediction
Comments NeurIPS 2020. Project page at: https://gammamodels.github.io/
When to Trust Your Model: Model-Based Policy Optimization
Comments NeurIPS 2019. Code at https://github.com/JannerM/mbpo, project page at: https://jannerm.github.io/mbpo-www/
Inter-Level Cooperation in Hierarchical Reinforcement Learning
AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale
Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Journal ref Conference on Robot Learning (2020)
TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
Autonomous Reinforcement Learning via Subgoal Curricula
Understanding the World Through Action
Comments Published in Conference on Robot Learning (CoRL) 2021, Blue Sky Track
