Alert button
Picture for Zhongwen Xu

Zhongwen Xu

Alert button

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

Sep 29, 2023
Shengyi Huang, Jiayi Weng, Rujikorn Charakorn, Min Lin, Zhongwen Xu, Santiago Ontañón

Viaarxiv icon

Visual Imitation Learning with Patch Rewards

Feb 10, 2023
Minghuan Liu, Tairan He, Weinan Zhang, Shuicheng Yan, Zhongwen Xu

Figure 1 for Visual Imitation Learning with Patch Rewards
Figure 2 for Visual Imitation Learning with Patch Rewards
Figure 3 for Visual Imitation Learning with Patch Rewards
Figure 4 for Visual Imitation Learning with Patch Rewards
Viaarxiv icon

Learning to Optimize for Reinforcement Learning

Feb 03, 2023
Qingfeng Lan, A. Rupam Mahmood, Shuicheng Yan, Zhongwen Xu

Figure 1 for Learning to Optimize for Reinforcement Learning
Figure 2 for Learning to Optimize for Reinforcement Learning
Figure 3 for Learning to Optimize for Reinforcement Learning
Figure 4 for Learning to Optimize for Reinforcement Learning
Viaarxiv icon

Reinforcement Learning from Diverse Human Preferences

Jan 30, 2023
Wanqi Xue, Bo An, Shuicheng Yan, Zhongwen Xu

Figure 1 for Reinforcement Learning from Diverse Human Preferences
Figure 2 for Reinforcement Learning from Diverse Human Preferences
Figure 3 for Reinforcement Learning from Diverse Human Preferences
Figure 4 for Reinforcement Learning from Diverse Human Preferences
Viaarxiv icon

Benchmarking Deformable Object Manipulation with Differentiable Physics

Oct 24, 2022
Siwei Chen, Cunjun Yu, Yiqing Xu, Linfeng Li, Xiao Ma, Zhongwen Xu, David Hsu

Figure 1 for Benchmarking Deformable Object Manipulation with Differentiable Physics
Figure 2 for Benchmarking Deformable Object Manipulation with Differentiable Physics
Figure 3 for Benchmarking Deformable Object Manipulation with Differentiable Physics
Figure 4 for Benchmarking Deformable Object Manipulation with Differentiable Physics
Viaarxiv icon

RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning

Oct 18, 2022
Wei Qiu, Xiao Ma, Bo An, Svetlana Obraztsova, Shuicheng Yan, Zhongwen Xu

Figure 1 for RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Figure 2 for RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Figure 3 for RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Figure 4 for RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Viaarxiv icon

Boosting Offline Reinforcement Learning via Data Rebalancing

Oct 17, 2022
Yang Yue, Bingyi Kang, Xiao Ma, Zhongwen Xu, Gao Huang, Shuicheng Yan

Figure 1 for Boosting Offline Reinforcement Learning via Data Rebalancing
Figure 2 for Boosting Offline Reinforcement Learning via Data Rebalancing
Figure 3 for Boosting Offline Reinforcement Learning via Data Rebalancing
Figure 4 for Boosting Offline Reinforcement Learning via Data Rebalancing
Viaarxiv icon

Mutual Information Regularized Offline Reinforcement Learning

Oct 14, 2022
Xiao Ma, Bingyi Kang, Zhongwen Xu, Min Lin, Shuicheng Yan

Figure 1 for Mutual Information Regularized Offline Reinforcement Learning
Figure 2 for Mutual Information Regularized Offline Reinforcement Learning
Figure 3 for Mutual Information Regularized Offline Reinforcement Learning
Figure 4 for Mutual Information Regularized Offline Reinforcement Learning
Viaarxiv icon

Efficient Offline Policy Optimization with a Learned Model

Oct 12, 2022
Zichen Liu, Siyi Li, Wee Sun Lee, Shuicheng Yan, Zhongwen Xu

Figure 1 for Efficient Offline Policy Optimization with a Learned Model
Figure 2 for Efficient Offline Policy Optimization with a Learned Model
Figure 3 for Efficient Offline Policy Optimization with a Learned Model
Figure 4 for Efficient Offline Policy Optimization with a Learned Model
Viaarxiv icon