作者
Sergey Levine
Robotics / Reinforcement Learning
Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
Comments 8 pages
Time-Contrastive Networks: Self-Supervised Learning from Video
Composable Deep Reinforcement Learning for Robotic Manipulation
Comments Videos: https://sites.google.com/view/composing-real-world-policies/
Stochastic Variational Video Prediction
Learning Flexible and Reusable Locomotion Primitives for a Microrobot
Comments 8 pages. Accepted at RAL+ICRA2018
Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
Meta-Reinforcement Learning of Structured Exploration Strategies
Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
Comments ICLR 2018
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
Comments First two authors contributed equally. Video available at https://sites.google.com/view/daml
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
Unifying Map and Landmark Based Representations for Visual Navigation
Comments Project page with videos: https://s-gupta.github.io/cmpl/
Sim2Real View Invariant Visual Servoing by Recurrent Control
Comments Supplementary video: https://fsadeghi.github.io/Sim2RealViewInvariantServo
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
Comments Videos of our experiments are available at: https://sites.google.com/site/mlleavenotrace/
End-to-End Learning of Semantic Grasping
Comments 14 pages
Learning with Latent Language
Learning Robotic Manipulation of Granular Media
Comments Proceedings of the Conference on Robot Learning 2017 (CoRL) (to appear)
Self-Supervised Visual Planning with Temporal Skip Connections
Comments accepted at the Conference on Robot Learning (CoRL) 2017
Backprop KF: Learning Discriminative Deterministic State Estimators
Comments NIPS 2016
Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
Comments 9 pages, 5 figures, 3 tables
Deep Object-Centric Representations for Generalizable Robot Learning
One-Shot Visual Imitation Learning via Meta-Learning
Comments Conference on Robot Learning, 2017 (to appear). First two authors contributed equally. Video available at https://sites.google.com/view/one-shot-imitation
GPLAC: Generalizing Vision-Based Robotic Skills using Weakly Labeled Images
Comments ICCV 2017. Also accepted at ICML 2017 Workshop on Lifelong Learning: A Reinforcement Learning Approach. Webpage: https://people.eecs.berkeley.edu/~avisingh/iccv17/
Reinforcement Learning with Deep Energy-Based Policies
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Comments ICML 2017. Code at https://github.com/cbfinn/maml, Videos of RL results at https://sites.google.com/view/maml, Blog post at http://bair.berkeley.edu/blog/2017/07/18/learning-to-learn/
Learning Visual Servoing with Deep Features and Fitted Q-Iteration
Comments ICLR 2017
Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning
Comments Paper accepted to the International Conference on Machine Learning (ICML) 2017
Modular Multitask Reinforcement Learning with Policy Sketches
Comments To appear at ICML 2017
