Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
Comments Published at CoRL 2019
作者
Sergey Levine
Robotics / Reinforcement Learning
Contextual Imagined Goals for Self-Supervised Robotic Learning
Comments 12 pages, to be presented at Conference on Robot Learning (CoRL) 2019. Project website: https://ccrig.github.io/
Probabilistic Model-Agnostic Meta-Learning
Comments NeurIPS 2018. First two authors contributed equally. Supplementary results available at https://sites.google.com/view/probabilistic-maml/
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
If MaxEnt RL is the Answer, What is the Question?
Deep Imitative Models for Flexible Inference, Planning, and Control
PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings
Comments To appear at the IEEE International Conference on Computer Vision (ICCV 2019). Website: https://sites.google.com/view/precog
SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
Deep Dynamics Models for Learning Dexterous Manipulation
Comments project website https://sites.google.com/view/pddm/
Soft Actor-Critic Algorithms and Applications
Comments arXiv admin note: substantial text overlap with arXiv:1801.01290
Meta-Learning with Implicit Gradients
Comments NeurIPS 2019. First two authors contributed equally
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks
Comments Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)
Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning
Comments Accepted to IROS and RA-L, 2019. For more information, see the website: https://sites.google.com/berkeley.edu/mbrl-quadrotor/. 9 pages, 12 figures
Online Meta-Learning
Comments ICML 2019. The first two authors contributed equally. Expanded Appendix
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Comments Preprint, Under Review
SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning
Comments ICML 2019. Project website: https://sites.google.com/view/icml19solar
Learning to Walk via Deep Reinforcement Learning
Comments RSS 2019, https://sites.google.com/view/minitaur-locomotion/
EMI: Exploration with Mutual Information
Comments Accepted and to appear at ICML 2019
Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
Comments Run our algorithm in your browser: http://bit.ly/rl_search
Learning Powerful Policies by Using Consistent Dynamics Model
Comments Accpted at RLDM 2019
Reinforcement Learning from Imperfect Demonstrations
Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search
Comments Submitted to the IEEE International Conference on Robotics and Automation 2017
MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning
Comments Extended version of paper accepted to ICRA 2019
End-to-End Robotic Reinforcement Learning without Reward Engineering
Comments Accepted to RSS 2019. 14 pages and 13 figures including references and appendix. Website: https://sites.google.com/view/reward-learning-rl/home
Automatically Composing Representation Transformations as a Means for Generalization
Comments Accepted to the International Conference on Learning Representations 2019
Data-efficient Learning of Morphology and Controller for a Microrobot
Comments Accepted at ICRA-2019. 6 pages
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight
Comments Videos available at https://sites.google.com/view/gvf-tool
