Sergey Levine

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

Dmitry Kalashnikov, Jacob Varley, Yevgen Chebotar, Benjamin Swanson, Rico Jonschkowski, Chelsea Finn, Sergey Levine, Karol Hausman

Conservative Safety Critics for Exploration

Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg

Comments Published as a conference paper in ICLR 2021

AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

Ashvin Nair, Abhishek Gupta, Murtaza Dalal, Sergey Levine

Comments 17 pages. Website: https://awacrl.github.io/

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

Soroush Nasiriany, Vitchyr H. Pong, Ashvin Nair, Alexander Khazatsky, Glen Berseth, Sergey Levine

Comments ICRA 2021

Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention

Abhishek Gupta, Justin Yu, Tony Z. Zhao, Vikash Kumar, Aaron Rovinsky, Kelvin Xu, Thomas Devlin, Sergey Levine

Comments Published at ICRA 2021. First four authors contributed equally

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

Nicholas Rhinehart, Jeff He, Charles Packer, Matthew A. Wright, Rowan McAllister, Joseph E. Gonzalez, Sergey Levine

Comments To be published at ICRA 2021. Project page: https://sites.google.com/view/contingency-planning

C-Learning: Learning to Achieve Goals via Recursive Classification

Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

Comments Accepted at ICLR 2021. Project website with videos (https://ben-eysenbach.github.io/c_learning/) and code (https://github.com/google-research/google-research/tree/master/c_learning) are online

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

Benjamin Eysenbach, Swapnil Asawa, Shreyas Chaudhari, Sergey Levine, Ruslan Salakhutdinov

Comments Published at ICLR 2021. Code (https://github.com/google-research/google-research/tree/master/darc) and blog post (https://blog.ml.cmu.edu/2020/07/31/maintaining-the-illusion-of-reality-transfer-in-rl-by-keeping-agents-in-the-darc)

Learning Invariant Representations for Reinforcement Learning without Reconstruction

Amy Zhang, Rowan McAllister, Roberto Calandra, Yarin Gal, Sergey Levine

Comments Accepted as an oral at ICLR 2021

Benchmarks for Deep Off-Policy Evaluation

Justin Fu, Mohammad Norouzi, Ofir Nachum, George Tucker, Ziyu Wang, Alexander Novikov, Mengjiao Yang, Michael R. Zhang, Yutian Chen, Aviral Kumar, Cosmin Paduraru, Sergey Levine, Tom Le Paine

Comments ICLR 2021 paper. Policies and evaluation code are available at https://github.com/google-research/deep_ope

Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots

Zhongyu Li, Xuxin Cheng, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath

Comments To appear on 2021 International Conference on Robotics and Automation (ICRA 2021)

Learning Human Objectives by Evaluating Hypothetical Behavior

Siddharth Reddy, Anca D. Dragan, Sergey Levine, Shane Legg, Jan Leike

Comments Published at International Conference on Machine Learning (ICML) 2020

Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation

Aurick Zhou, Sergey Levine

Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation

Justin Fu, Sergey Levine

SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments

Glen Berseth, Daniel Geng, Coline Devin, Nicholas Rhinehart, Chelsea Finn, Dinesh Jayaraman, Sergey Levine

Comments ICLR 2021

D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine

Comments Website available at https://sites.google.com/view/d4rl/home

How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned

Julian Ibarz, Jie Tan, Chelsea Finn, Mrinal Kalakrishnan, Peter Pastor, Sergey Levine

Journal ref Journal of Robotics Research (IJRR), February 2021

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

Michael Dennis, Natasha Jaques, Eugene Vinitsky, Alexandre Bayen, Stuart Russell, Andrew Critch, Sergey Levine

Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads

Suneel Belkhale, Rachel Li, Gregory Kahn, Rowan McAllister, Roberto Calandra, Sergey Levine

Journal ref IEEE Robotics and Automation Letters 2021

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, Dinesh Jayaraman

Comments 15 pages, 8 figures, ICML 2020. Website with code: https://sites.google.com/berkeley.edu/carl

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:11055-11065, 2020

Adversarial Policies: Attacking Deep Reinforcement Learning

Adam Gleave, Michael Dennis, Cody Wild, Neel Kant, Sergey Levine, Stuart Russell

Comments Presented at ICLR 2020

MELD: Meta-Reinforcement Learning from Images via Latent State Models

Tony Z. Zhao, Anusha Nagabandi, Kate Rakelly, Chelsea Finn, Sergey Levine

Comments Accepted to CoRL 2020. Supplementary material at https://sites.google.com/view/meld-lsm/home . 16 pages, 19 figures. V2: add funding acknowledgements, reduce file size

Model-Based Visual Planning with Self-Supervised Functional Distances

Stephen Tian, Suraj Nair, Frederik Ebert, Sudeep Dasari, Benjamin Eysenbach, Chelsea Finn, Sergey Levine

Gradient Surgery for Multi-Task Learning

Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn

Comments NeurIPS 2020. Code is available at https://github.com/tianheyu927/PCGrad

Variable-Shot Adaptation for Online Meta-Learning

Tianhe Yu, Xinyang Geng, Chelsea Finn, Sergey Levine

Comments First two authors contribute equally

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

Mohammad Babaeizadeh, Mohammad Taghi Saffar, Danijar Hafner, Harini Kannan, Chelsea Finn, Sergey Levine, Dumitru Erhan

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn

Comments Accepted at NeurIPS 2020

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Karl Pertsch, Oleh Rybkin, Frederik Ebert, Chelsea Finn, Dinesh Jayaraman, Sergey Levine

Comments Project page: orybkin.github.io/video-gcp. KP and OR contributed equally

MOPO: Model-based Offline Policy Optimization

Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma

Comments NeurIPS 2020. First two authors contributed equally. Last two authors advised equally

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

Avi Singh, Huihan Liu, Gaoyue Zhou, Albert Yu, Nicholas Rhinehart, Sergey Levine

Comments First two authors contributed equally. Project website: https://sites.google.com/view/parrot-rl