Alert button
Picture for Sergey Levine

Sergey Levine

Alert button

AW-Opt: Learning Robotic Skills with Imitation andReinforcement at Scale

Nov 09, 2021
Yao Lu, Karol Hausman, Yevgen Chebotar, Mengyuan Yan, Eric Jang, Alexander Herzog, Ted Xiao, Alex Irpan, Mohi Khansari, Dmitry Kalashnikov, Sergey Levine

Figure 1 for AW-Opt: Learning Robotic Skills with Imitation andReinforcement at Scale
Figure 2 for AW-Opt: Learning Robotic Skills with Imitation andReinforcement at Scale
Figure 3 for AW-Opt: Learning Robotic Skills with Imitation andReinforcement at Scale
Figure 4 for AW-Opt: Learning Robotic Skills with Imitation andReinforcement at Scale
Viaarxiv icon

Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning

Nov 04, 2021
Dhruv Shah, Peng Xu, Yao Lu, Ted Xiao, Alexander Toshev, Sergey Levine, Brian Ichter

Figure 1 for Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Figure 2 for Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Figure 3 for Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Figure 4 for Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Viaarxiv icon

TRAIL: Near-Optimal Imitation Learning with Suboptimal Data

Oct 27, 2021
Mengjiao Yang, Sergey Levine, Ofir Nachum

Figure 1 for TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
Figure 2 for TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
Figure 3 for TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
Figure 4 for TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
Viaarxiv icon

Understanding the World Through Action

Oct 24, 2021
Sergey Levine

Viaarxiv icon

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks

Oct 22, 2021
Tianjun Zhang, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Joseph E. Gonzalez

Figure 1 for C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks
Figure 2 for C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks
Figure 3 for C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks
Figure 4 for C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks
Viaarxiv icon

Data-Driven Offline Optimization For Architecting Hardware Accelerators

Oct 20, 2021
Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine

Figure 1 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
Figure 2 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
Figure 3 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
Figure 4 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
Viaarxiv icon

MEMO: Test Time Robustness via Adaptation and Augmentation

Oct 18, 2021
Marvin Zhang, Sergey Levine, Chelsea Finn

Figure 1 for MEMO: Test Time Robustness via Adaptation and Augmentation
Figure 2 for MEMO: Test Time Robustness via Adaptation and Augmentation
Figure 3 for MEMO: Test Time Robustness via Adaptation and Augmentation
Figure 4 for MEMO: Test Time Robustness via Adaptation and Augmentation
Viaarxiv icon

Offline Meta-Reinforcement Learning for Industrial Insertion

Oct 12, 2021
Tony Z. Zhao, Jianlan Luo, Oleg Sushkov, Rugile Pevceviciute, Nicolas Heess, Jon Scholz, Stefan Schaal, Sergey Levine

Figure 1 for Offline Meta-Reinforcement Learning for Industrial Insertion
Figure 2 for Offline Meta-Reinforcement Learning for Industrial Insertion
Figure 3 for Offline Meta-Reinforcement Learning for Industrial Insertion
Figure 4 for Offline Meta-Reinforcement Learning for Industrial Insertion
Viaarxiv icon

Offline Reinforcement Learning with Implicit Q-Learning

Oct 12, 2021
Ilya Kostrikov, Ashvin Nair, Sergey Levine

Figure 1 for Offline Reinforcement Learning with Implicit Q-Learning
Figure 2 for Offline Reinforcement Learning with Implicit Q-Learning
Figure 3 for Offline Reinforcement Learning with Implicit Q-Learning
Figure 4 for Offline Reinforcement Learning with Implicit Q-Learning
Viaarxiv icon

Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World

Oct 11, 2021
Laura Smith, J. Chase Kew, Xue Bin Peng, Sehoon Ha, Jie Tan, Sergey Levine

Figure 1 for Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
Figure 2 for Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
Figure 3 for Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
Figure 4 for Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
Viaarxiv icon