Alert button
Picture for Sergey Levine

Sergey Levine

Alert button

Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play

Feb 17, 2019
Reza Mahjourian, Risto Miikkulainen, Nevena Lazic, Sergey Levine, Navdeep Jaitly

Figure 1 for Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play
Figure 2 for Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play
Figure 3 for Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play
Figure 4 for Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play
Viaarxiv icon

Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight

Feb 11, 2019
Katie Kang, Suneel Belkhale, Gregory Kahn, Pieter Abbeel, Sergey Levine

Figure 1 for Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
Figure 2 for Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
Figure 3 for Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
Figure 4 for Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
Viaarxiv icon

InfoBot: Transfer and Exploration via the Information Bottleneck

Feb 07, 2019
Anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Matthew Botvinick, Hugo Larochelle, Yoshua Bengio, Sergey Levine

Figure 1 for InfoBot: Transfer and Exploration via the Information Bottleneck
Figure 2 for InfoBot: Transfer and Exploration via the Information Bottleneck
Figure 3 for InfoBot: Transfer and Exploration via the Information Bottleneck
Figure 4 for InfoBot: Transfer and Exploration via the Information Bottleneck
Viaarxiv icon

Cognitive Mapping and Planning for Visual Navigation

Feb 07, 2019
Saurabh Gupta, Varun Tolani, James Davidson, Sergey Levine, Rahul Sukthankar, Jitendra Malik

Figure 1 for Cognitive Mapping and Planning for Visual Navigation
Figure 2 for Cognitive Mapping and Planning for Visual Navigation
Figure 3 for Cognitive Mapping and Planning for Visual Navigation
Viaarxiv icon

Artificial Intelligence for Prosthetics - challenge solutions

Feb 07, 2019
Łukasz Kidziński, Carmichael Ong, Sharada Prasanna Mohanty, Jennifer Hicks, Sean F. Carroll, Bo Zhou, Hongsheng Zeng, Fan Wang, Rongzhong Lian, Hao Tian, Wojciech Jaśkowski, Garrett Andersen, Odd Rune Lykkebø, Nihat Engin Toklu, Pranav Shyam, Rupesh Kumar Srivastava, Sergey Kolesnikov, Oleksii Hrinchuk, Anton Pechenko, Mattias Ljungström, Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang, Aleksei Shpilman, Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Lance Rane, Aditya Bhatt, Zhengfei Wang, Penghui Qi, Zeyang Yu, Peng Peng, Quan Yuan, Wenxin Li, Yunsheng Tian, Ruihan Yang, Pingchuan Ma, Shauharda Khadka, Somdeb Majumdar, Zach Dwiel, Yinyin Liu, Evren Tumer, Jeremy Watson, Marcel Salathé, Sergey Levine, Scott Delp

Figure 1 for Artificial Intelligence for Prosthetics - challenge solutions
Figure 2 for Artificial Intelligence for Prosthetics - challenge solutions
Figure 3 for Artificial Intelligence for Prosthetics - challenge solutions
Figure 4 for Artificial Intelligence for Prosthetics - challenge solutions
Viaarxiv icon

Deep Imitative Models for Flexible Inference, Planning, and Control

Jan 31, 2019
Nicholas Rhinehart, Rowan McAllister, Sergey Levine

Figure 1 for Deep Imitative Models for Flexible Inference, Planning, and Control
Figure 2 for Deep Imitative Models for Flexible Inference, Planning, and Control
Figure 3 for Deep Imitative Models for Flexible Inference, Planning, and Control
Figure 4 for Deep Imitative Models for Flexible Inference, Planning, and Control
Viaarxiv icon

Soft Actor-Critic Algorithms and Applications

Jan 29, 2019
Tuomas Haarnoja, Aurick Zhou, Kristian Hartikainen, George Tucker, Sehoon Ha, Jie Tan, Vikash Kumar, Henry Zhu, Abhishek Gupta, Pieter Abbeel, Sergey Levine

Figure 1 for Soft Actor-Critic Algorithms and Applications
Figure 2 for Soft Actor-Critic Algorithms and Applications
Figure 3 for Soft Actor-Critic Algorithms and Applications
Figure 4 for Soft Actor-Critic Algorithms and Applications
Viaarxiv icon

Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL

Jan 28, 2019
Anusha Nagabandi, Chelsea Finn, Sergey Levine

Figure 1 for Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
Figure 2 for Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
Figure 3 for Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
Figure 4 for Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
Viaarxiv icon

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement learning

Jan 11, 2019
Nathan O. Lambert, Daniel S. Drew, Joseph Yaconelli, Roberto Calandra, Sergey Levine, Kristofer S. J. Pister

Figure 1 for Low Level Control of a Quadrotor with Deep Model-Based Reinforcement learning
Figure 2 for Low Level Control of a Quadrotor with Deep Model-Based Reinforcement learning
Figure 3 for Low Level Control of a Quadrotor with Deep Model-Based Reinforcement learning
Figure 4 for Low Level Control of a Quadrotor with Deep Model-Based Reinforcement learning
Viaarxiv icon

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning

Jan 07, 2019
Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu

Figure 1 for Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Figure 2 for Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Figure 3 for Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Figure 4 for Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Viaarxiv icon