Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Xu He

Xu He

RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents


Feb 17, 2021
Wei Qiu, Xinrun Wang, Runsheng Yu, Xu He, Rundong Wang, Bo An, Svetlana Obraztsova, Zinovi Rabinovich

Figure 1 for RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
Figure 2 for RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
Figure 3 for RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
Figure 4 for RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents

  Access Paper or Ask Questions

Personalized Adaptive Meta Learning for Cold-start User Preference Prediction


Dec 22, 2020
Runsheng Yu, Yu Gong, Xu He, Bo An, Yu Zhu, Qingwen Liu, Wenwu Ou

Figure 1 for Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
Figure 2 for Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
Figure 3 for Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
Figure 4 for Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
* Preprint Version 
  Access Paper or Ask Questions

Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication


Aug 29, 2020
Xu He, Bo An, Yanghua Li, Haikai Chen, Rundong Wang, Xinrun Wang, Runsheng Yu, Xin Li, Zhirong Wang

Figure 1 for Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
Figure 2 for Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
Figure 3 for Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
Figure 4 for Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication

  Access Paper or Ask Questions

Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation


Aug 21, 2020
Xu He, Bo An, Yanghua Li, Haikai Chen, Qingyu Guo, Xin Li, Zhirong Wang

Figure 1 for Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation
Figure 2 for Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation
Figure 3 for Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation
Figure 4 for Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation

  Access Paper or Ask Questions

Continual Learning from the Perspective of Compression


Jun 26, 2020
Xu He, Min Lin

Figure 1 for Continual Learning from the Perspective of Compression
Figure 2 for Continual Learning from the Perspective of Compression
Figure 3 for Continual Learning from the Perspective of Compression
Figure 4 for Continual Learning from the Perspective of Compression
* 4th Lifelong Learning Workshop at ICML 2020 
  Access Paper or Ask Questions

Learning Behaviors with Uncertain Human Feedback


Jun 07, 2020
Xu He, Haipeng Chen, Bo An

Figure 1 for Learning Behaviors with Uncertain Human Feedback
Figure 2 for Learning Behaviors with Uncertain Human Feedback
Figure 3 for Learning Behaviors with Uncertain Human Feedback
Figure 4 for Learning Behaviors with Uncertain Human Feedback

  Access Paper or Ask Questions

Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving


May 23, 2020
Donghao Xu, Zhezhang Ding, Xu He, Huijing Zhao, Mathieu Moze, François Aioun, Franck Guillemard

Figure 1 for Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving
Figure 2 for Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving
Figure 3 for Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving
Figure 4 for Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving
* 14 pages, 9 figures. Submitted to T.ITS 
  Access Paper or Ask Questions

Learning Efficient Multi-agent Communication: An Information Bottleneck Approach


Nov 16, 2019
Rundong Wang, Xu He, Runsheng Yu, Wei Qiu, Bo An, Zinovi Rabinovich

Figure 1 for Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Figure 2 for Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Figure 3 for Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Figure 4 for Learning Efficient Multi-agent Communication: An Information Bottleneck Approach

  Access Paper or Ask Questions

Task Agnostic Continual Learning via Meta Learning


Jun 12, 2019
Xu He, Jakub Sygnowski, Alexandre Galashov, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu

Figure 1 for Task Agnostic Continual Learning via Meta Learning
Figure 2 for Task Agnostic Continual Learning via Meta Learning
Figure 3 for Task Agnostic Continual Learning via Meta Learning
Figure 4 for Task Agnostic Continual Learning via Meta Learning

  Access Paper or Ask Questions

CSI-Net: Unified Human Body Characterization and Action Recognition


Oct 07, 2018
Fei Wang, Jinsong Han, Shiyuan Zhang, Xu He, Dong Huang

Figure 1 for CSI-Net: Unified Human Body Characterization and Action Recognition
Figure 2 for CSI-Net: Unified Human Body Characterization and Action Recognition
Figure 3 for CSI-Net: Unified Human Body Characterization and Action Recognition
Figure 4 for CSI-Net: Unified Human Body Characterization and Action Recognition
* 30 pages, 14 figures and 19 tables 
  Access Paper or Ask Questions

Overcoming Catastrophic Interference by Conceptors


Jul 20, 2017
Xu He, Herbert Jaeger

Figure 1 for Overcoming Catastrophic Interference by Conceptors
Figure 2 for Overcoming Catastrophic Interference by Conceptors
Figure 3 for Overcoming Catastrophic Interference by Conceptors
Figure 4 for Overcoming Catastrophic Interference by Conceptors
* 14 pages, 4 figures 
  Access Paper or Ask Questions