Alert button
Picture for Sergey Levine

Sergey Levine

Alert button

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives

Jun 25, 2019
Anirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio

Figure 1 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Figure 2 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Figure 3 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Figure 4 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Viaarxiv icon

Off-Policy Evaluation via Off-Policy Classification

Jun 20, 2019
Alex Irpan, Kanishka Rao, Konstantinos Bousmalis, Chris Harris, Julian Ibarz, Sergey Levine

Figure 1 for Off-Policy Evaluation via Off-Policy Classification
Figure 2 for Off-Policy Evaluation via Off-Policy Classification
Figure 3 for Off-Policy Evaluation via Off-Policy Classification
Figure 4 for Off-Policy Evaluation via Off-Policy Classification
Viaarxiv icon

When to Trust Your Model: Model-Based Policy Optimization

Jun 19, 2019
Michael Janner, Justin Fu, Marvin Zhang, Sergey Levine

Figure 1 for When to Trust Your Model: Model-Based Policy Optimization
Figure 2 for When to Trust Your Model: Model-Based Policy Optimization
Figure 3 for When to Trust Your Model: Model-Based Policy Optimization
Figure 4 for When to Trust Your Model: Model-Based Policy Optimization
Viaarxiv icon

SQIL: Imitation Learning via Regularized Behavioral Cloning

Jun 14, 2019
Siddharth Reddy, Anca D. Dragan, Sergey Levine

Figure 1 for SQIL: Imitation Learning via Regularized Behavioral Cloning
Figure 2 for SQIL: Imitation Learning via Regularized Behavioral Cloning
Figure 3 for SQIL: Imitation Learning via Regularized Behavioral Cloning
Figure 4 for SQIL: Imitation Learning via Regularized Behavioral Cloning
Viaarxiv icon

Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards

Jun 13, 2019
Gerrit Schoettler, Ashvin Nair, Jianlan Luo, Shikhar Bahl, Juan Aparicio Ojea, Eugen Solowjow, Sergey Levine

Figure 1 for Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
Figure 2 for Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
Figure 3 for Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
Figure 4 for Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
Viaarxiv icon

Efficient Exploration via State Marginal Matching

Jun 12, 2019
Lisa Lee, Benjamin Eysenbach, Emilio Parisotto, Eric Xing, Sergey Levine, Ruslan Salakhutdinov

Figure 1 for Efficient Exploration via State Marginal Matching
Figure 2 for Efficient Exploration via State Marginal Matching
Figure 3 for Efficient Exploration via State Marginal Matching
Figure 4 for Efficient Exploration via State Marginal Matching
Viaarxiv icon

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning

Jun 12, 2019
Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

Figure 1 for Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
Figure 2 for Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
Figure 3 for Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
Figure 4 for Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
Viaarxiv icon

Learning Powerful Policies by Using Consistent Dynamics Model

Jun 11, 2019
Shagun Sodhani, Anirudh Goyal, Tristan Deleu, Yoshua Bengio, Sergey Levine, Jian Tang

Figure 1 for Learning Powerful Policies by Using Consistent Dynamics Model
Figure 2 for Learning Powerful Policies by Using Consistent Dynamics Model
Figure 3 for Learning Powerful Policies by Using Consistent Dynamics Model
Figure 4 for Learning Powerful Policies by Using Consistent Dynamics Model
Viaarxiv icon

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

Jun 07, 2019
Allan Zhou, Eric Jang, Daniel Kappler, Alex Herzog, Mohi Khansari, Paul Wohlhart, Yunfei Bai, Mrinal Kalakrishnan, Sergey Levine, Chelsea Finn

Figure 1 for Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
Figure 2 for Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
Figure 3 for Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
Figure 4 for Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
Viaarxiv icon