Regret Minimization for Partially Observable Deep Reinforcement Learning
Comments ICML 2018
作者
Sergey Levine
Robotics / Reinforcement Learning
Time-Agnostic Prediction: Predicting Predictable Video Frames
Comments 8 pages, plus appendices
Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation
Comments Accepted to the Conference on Robot Learning (CoRL) 2018. Video at https://youtu.be/lOLT7zifEkg
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost
Comments https://sites.google.com/view/deeprl-handmanipulation
SFV: Reinforcement Learning of Physical Skills from Videos
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
Path Integral Guided Policy Search
Comments Published at the International Conference on Robotics and Automation (ICRA), 2017
Diversity is All You Need: Learning Skills without a Reward Function
Comments Videos and code for our experiments are available at: https://sites.google.com/view/diayn
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning
Comments accepted at the Conference on Robot Learning (CoRL) 2018
Data-Efficient Hierarchical Reinforcement Learning
Comments NIPS 2018
Few-Shot Goal Inference for Visuomotor Learning and Planning
Comments Videos available at https://sites.google.com/view/few-shot-goals
Latent Space Policies for Hierarchical Reinforcement Learning
Comments ICML 2018; Videos: https://sites.google.com/view/latent-space-deep-rl Code: https://github.com/haarnoja/sac
Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
Comments ICML 2018 Videos: sites.google.com/view/soft-actor-critic Code: github.com/haarnoja/sac
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
Comments 8 pages. Published on IEEE Robotics and Automation Letters (RAL). Website: https://sites.google.com/view/more-than-a-feeling
Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Comments Accepted for presentation at Robotics: Science and Systems (RSS) 2018. Project page: https://sites.google.com/view/deeprl-dexterous-manipulation
Learning Instance Segmentation by Interaction
Comments Website at https://pathak22.github.io/seg-by-interaction/
Few-Shot Segmentation Propagation with Guided Networks
Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
Comments Accepted at ICRA 2018, Brisbane. YuXuan Liu and Abhishek Gupta had equal contribution
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
Comments Accepted at ICML 2018
Shared Autonomy via Deep Reinforcement Learning
Comments Accepted to the Robotics: Science and Systems (RSS) 2018 conference
Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation
Comments ICRA 2018
Divide-and-Conquer Reinforcement Learning
Comments Presented at ICLR 2018. Videos and supporting materials are located at http://bit.ly/dnc-rl
Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration
Stochastic Adversarial Video Prediction
Comments Website: https://alexlee-gk.github.io/video_prediction/
Universal Planning Networks
Comments Videos available at https://sites.google.com/view/upn-public/home
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments
Comments 27 pages, 17 figures
Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning
Comments 16 pages, 8 figures, a competition at NIPS 2017
