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 Deheng Ye

Deheng Ye
Alert button

Tencent Inc

Deploying Offline Reinforcement Learning with Human Feedback


Mar 13, 2023
Ziniu Li, Ke Xu, Liu Liu, Lanqing Li, Deheng Ye, Peilin Zhao

Add code
Alert button

Figure 1 for Deploying Offline Reinforcement Learning with Human Feedback
Figure 2 for Deploying Offline Reinforcement Learning with Human Feedback
Figure 3 for Deploying Offline Reinforcement Learning with Human Feedback
Figure 4 for Deploying Offline Reinforcement Learning with Human Feedback

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization


Feb 05, 2023
Zichuan Lin, Xiapeng Wu, Mingfei Sun, Deheng Ye, Qiang Fu, Wei Yang, Wei Liu

Add code
Alert button

Figure 1 for Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Figure 2 for Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Figure 3 for Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Figure 4 for Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning


Jan 20, 2023
Haoxuan Pan, Deheng Ye, Xiaoming Duan, Qiang Fu, Wei Yang, Jianping He, Mingfei Sun

Add code
Alert button

Figure 1 for Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning
Figure 2 for Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning
Figure 3 for Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning
Figure 4 for Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning
* 12 pages, 9 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Survey on Transformers in Reinforcement Learning


Jan 08, 2023
Wenzhe Li, Hao Luo, Zichuan Lin, Chongjie Zhang, Zongqing Lu, Deheng Ye

Add code
Alert button

Figure 1 for A Survey on Transformers in Reinforcement Learning
Figure 2 for A Survey on Transformers in Reinforcement Learning
Figure 3 for A Survey on Transformers in Reinforcement Learning

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning


Dec 13, 2022
Boxuan Zhao, Jun Zhang, Deheng Ye, Jian Cao, Xiao Han, Qiang Fu, Wei Yang

Add code
Alert button

Figure 1 for RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Figure 2 for RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Figure 3 for RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Figure 4 for RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
* accepted by AAAI 2023 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pretraining in Deep Reinforcement Learning: A Survey


Nov 08, 2022
Zhihui Xie, Zichuan Lin, Junyou Li, Shuai Li, Deheng Ye

Add code
Alert button

Figure 1 for Pretraining in Deep Reinforcement Learning: A Survey
Figure 2 for Pretraining in Deep Reinforcement Learning: A Survey
Figure 3 for Pretraining in Deep Reinforcement Learning: A Survey
Figure 4 for Pretraining in Deep Reinforcement Learning: A Survey

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Curriculum-based Asymmetric Multi-task Reinforcement Learning


Nov 07, 2022
Hanchi Huang, Deheng Ye, Li Shen, Wei Liu

Add code
Alert button

Figure 1 for Curriculum-based Asymmetric Multi-task Reinforcement Learning
Figure 2 for Curriculum-based Asymmetric Multi-task Reinforcement Learning
Figure 3 for Curriculum-based Asymmetric Multi-task Reinforcement Learning
Figure 4 for Curriculum-based Asymmetric Multi-task Reinforcement Learning
* Accepted by TPAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation


Oct 19, 2022
Chengqian Gao, Ke Xu, Liu Liu, Deheng Ye, Peilin Zhao, Zhiqiang Xu

Add code
Alert button

Figure 1 for Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
Figure 2 for Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
Figure 3 for Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
Figure 4 for Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
* 9 pages, under review 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning


Oct 09, 2022
Hua Wei, Jingxiao Chen, Xiyang Ji, Hongyang Qin, Minwen Deng, Siqin Li, Liang Wang, Weinan Zhang, Yong Yu, Lin Liu, Lanxiao Huang, Deheng Ye, Qiang Fu, Wei Yang

Add code
Alert button

Figure 1 for Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
Figure 2 for Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
Figure 3 for Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
Figure 4 for Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
* Accepted by NeurIPS 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>