作者
Sergey Levine
Robotics / Reinforcement Learning
Unsupervised Learning via Meta-Learning
Comments ICLR 2019 camera-ready. 24 pages, 2 figures, links to code available at https://sites.google.com/view/unsupervised-via-meta
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
Manipulation by Feel: Touch-Based Control with Deep Predictive Models
Comments Accepted to ICRA 2019
Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matching
Comments 6 pages; accepted to IEEE International Conference on Robotics and Automation 2019 (ICRA 2019)
Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
Comments First 2 authors contributed equally. Website: https://sites.google.com/berkeley.edu/metaadaptivecontrol
Diagnosing Bottlenecks in Deep Q-learning Algorithms
From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play
Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
Comments First three authors contributed equally. Accepted to ICRA 2019
Artificial Intelligence for Prosthetics - challenge solutions
Cognitive Mapping and Planning for Visual Navigation
Comments Extended IJCV Version of the original paper at CVPR17. Project website with code, models, simulation environment and videos: https://sites.google.com/view/cognitive-mapping-and-planning/
Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
Comments Project website: https://sites.google.com/berkeley.edu/onlineviameta
Guiding Policies with Language via Meta-Learning
Comments Accepted at ICLR 2019
Learning Actionable Representations with Goal-Conditioned Policies
Comments To be presented at ICLR 2019
Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Comments Accepted at ICLR 2019
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
Comments ICLR 2019 Conference Paper
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Comments ICLR 2019, project page: https://people.eecs.berkeley.edu/~janner/o2p2/
Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior
Comments Accepted at Neural Information Processing Systems (NeurIPS) 2018
Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty
Residual Reinforcement Learning for Robot Control
Comments 7 pages
Visual Reinforcement Learning with Imagined Goals
Comments 15 pages, NeurIPS 2018
Visual Memory for Robust Path Following
Comments Neural Information Processing Systems (NeurIPS) 2018. Oral Presentation
Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Comments CoRL 2018 camera ready. 23 pages, 14 figures
Grasp2Vec: Learning Object Representations from Self-Supervised Grasping
Comments CoRL 2018. Eric Jang and Coline Devin contributed equally to this work
Journal ref Proceedings of The 2nd Conference on Robot Learning, in PMLR 87:99-112 (2018)
The Mirage of Action-Dependent Baselines in Reinforcement Learning
Comments Updated to ICML final submission
Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition
Comments First two authors contributed equally. Accepted to NIPS. Website: https://sites.google.com/view/inverse-event
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
Comments NIPS 2018, video and code available at https://sites.google.com/view/drl-in-a-handful-of-trials/
One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
Comments Video results available at https://sites.google.com/view/one-shot-hil
