A Workflow for Offline Model-Free Robotic Reinforcement Learning
Comments CoRL 2021. Project Website: https://sites.google.com/view/offline-rl-workflow. First two authors contributed equally
作者
Chelsea Finn
Robotics / Machine Learning
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
Measuring and Harnessing Transference in Multi-Task Learning
Offline Meta-Reinforcement Learning with Advantage Weighting
Comments ICML 2021; for code & project info, see http://sites.google.com/view/macaw-metarl
WILDS: A Benchmark of in-the-Wild Distribution Shifts
FitVid: Overfitting in Pixel-Level Video Prediction
Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
Comments Equal advising and contribution for last two authors
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
Comments This is an update version of a manuscript that originally appeared at CoRL 2019. Videos are here: meta-world.github.io, open-sourced code are available at: https://github.com/rlworkgroup/metaworld, and the baselines can be found at https://github.com/rlworkgroup/garage
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Comments RA-L and ICRA 2021. First two authors contributed equally
Journal ref Robotics and Automation Letters (RA-L) and International Conference on Robotics and Automation (ICRA) 2021
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
Batch Exploration with Examples for Scalable Robotic Reinforcement Learning
Comments 11 Pages, 11 Figures
Journal ref IEEE Robotics and Automation Letters ( Volume: 6, Issue: 3, July 2021)
Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos
Discriminator Augmented Model-Based Reinforcement Learning
Meta-Learning Symmetries by Reparameterization
Comments ICLR 2021
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms
SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
Comments ICLR 2021
How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
Journal ref Journal of Robotics Research (IJRR), February 2021
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
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
MELD: Meta-Reinforcement Learning from Images via Latent State Models
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
Gradient Surgery for Multi-Task Learning
Comments NeurIPS 2020. Code is available at https://github.com/tianheyu927/PCGrad
Offline Reinforcement Learning from Images with Latent Space Models
Variable-Shot Adaptation for Online Meta-Learning
Comments First two authors contribute equally
Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
Comments Accepted at NeurIPS 2020
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Comments Project page: orybkin.github.io/video-gcp. KP and OR contributed equally
MOPO: Model-based Offline Policy Optimization
Comments NeurIPS 2020. First two authors contributed equally. Last two authors advised equally
Weakly-Supervised Reinforcement Learning for Controllable Behavior
Comments Published in NeurIPS 2020
Learning Latent Representations to Influence Multi-Agent Interaction
Comments Conference on Robot Learning (CoRL) 2020. Supplementary website at https://sites.google.com/view/latent-strategies/
