作者
Sergey Levine
Robotics / Reinforcement Learning
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Comments Type/Token Distinction in Deep learning Framework
Continual Learning of Control Primitives: Skill Discovery via Reset-Games
Comments To appear at NeurIPS 2020
Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting
Comments Published in Conference on Robot Learning (CoRL), 2020. Project webpage: http://www.xinshuoweng.com/projects/SPF2/
Rearrangement: A Challenge for Embodied AI
Comments Authors are listed in alphabetical order
Learning to Walk in the Real World with Minimal Human Effort
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
Comments Accepted to CoRL 2020. Source code and videos available at https://sites.google.com/view/cog-rl
Guided Meta-Policy Search
Comments Published at Neurips 2019. Website : https://sites.google.com/berkeley.edu/guided-metapolicy-search
Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
Comments Project website: https://alexlee-gk.github.io/slac/
LaND: Learning to Navigate from Disengagements
Learning to Reach Goals via Iterated Supervised Learning
Comments First two authors contributed equally. Code available at https://github.com/dibyaghosh/gcsl
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Comments The first two authors contributed equally. Accepted at ICML 2020. Supplementary videos and code available at: https://sites.google.com/view/av-detect-recover-adapt
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
Conservative Q-Learning for Offline Reinforcement Learning
Comments Preprint. Website at: https://sites.google.com/view/cql-offline-rl
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
Comments 18 pages, 13 figures, accepted to the International Conference on Machine Learning (ICML) 2020
Assisted Perception: Optimizing Observations to Communicate State
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
Comments ICML 2020. 8 pages, 8 figures; 9 pages appendix (6 additional figures)
Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control
Comments In NeurIPS 2019
Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning
Comments 8.5 pages, 9 figures. See video overview and experiments at https://youtu.be/pPDVewcSpdc and project website at https://ryanjulian.me/continual-fine-tuning
Learning Agile Robotic Locomotion Skills by Imitating Animals
Ecological Reinforcement Learning
Comments Preprint. Website at: https://sites.google.com/view/ecological-rl/home
AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos
Comments Robotics: Science and Systems (RSS) 2020 camera ready submission. Project website: https://sites.google.com/view/rss20avid
RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real
Comments Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020)
Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling
Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks
Comments 9 pages, 8 figures
Time Reversal as Self-Supervision
Comments 7 pages, 10 figures
Journal ref International Conference on Robotics and Automation, 2020
Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
Comments Robotics and Automation Letters and International Conference on Robotics and Automation 2020. First two authors contributed equally
Journal ref Robotics and Automation Letters 2020
Entity Abstraction in Visual Model-Based Reinforcement Learning
Comments Accepted at CoRL 2019
Unsupervised Meta-Learning for Reinforcement Learning
Comments First two authors contributed equally
