Hongyao Tang

State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning

Nov 28, 2022
Chen Chen, Hongyao Tang, Yi Ma, Chao Wang, Qianli Shen, Dong Li, Jianye Hao

Figure 2 for State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning

Figure 3 for State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning

Figure 4 for State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning

Access Paper or Ask Questions

ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation

Oct 26, 2022
Pengyi Li, Hongyao Tang, Jianye Hao, Yan Zheng, Xian Fu, Zhaopeng Meng

Figure 2 for ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation

Figure 3 for ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation

Figure 4 for ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation

* The paper has been accpeted by Deep Reinforcement Learning Workshop, NeurIPS 2022

Access Paper or Ask Questions

Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes

Sep 16, 2022
Min Zhang, Hongyao Tang, Jianye Hao, Yan Zheng

Figure 2 for Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes

Figure 3 for Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes

Figure 4 for Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes

* Preprint version

Access Paper or Ask Questions

PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations

Apr 06, 2022
Tong Sang, Hongyao Tang, Yi Ma, Jianye Hao, Yan Zheng, Zhaopeng Meng, Boyan Li, Zhen Wang

Figure 2 for PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations

Figure 3 for PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations

Figure 4 for PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations

* Preprint, work presented at the Generalizable Policy Learning in the Physical World Workshop (ICLR 2022)

Access Paper or Ask Questions

PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

Mar 16, 2022
Pengyi Li, Hongyao Tang, Tianpei Yang, Xiaotian Hao, Tong Sang, Yan Zheng, Jianye Hao, Matthew E. Taylor, Zhen Wang

Figure 2 for PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

Figure 3 for PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

Figure 4 for PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

* A preliminary version has been accepted on the Cooperative AI Workshop at 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

Access Paper or Ask Questions

ED2: An Environment Dynamics Decomposition Framework for World Model Construction

Dec 06, 2021
Cong Wang, Tianpei Yang, Jianye Hao, Yan Zheng, Hongyao Tang, Fazl Barez, Jinyi Liu, Jiajie Peng, Haiyin Piao, Zhixiao Sun

Figure 2 for ED2: An Environment Dynamics Decomposition Framework for World Model Construction

Figure 3 for ED2: An Environment Dynamics Decomposition Framework for World Model Construction

Figure 4 for ED2: An Environment Dynamics Decomposition Framework for World Model Construction

Access Paper or Ask Questions

Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning

Nov 19, 2021
Tong Sang, Hongyao Tang, Jianye Hao, Yan Zheng, Zhaopeng Meng

Figure 2 for Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning

Figure 3 for Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning

Figure 4 for Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning

* This paper is accepted by The 3rd International Conference on Distributed Artificial Intelligence (DAI 2021, Shanghai, China)

Access Paper or Ask Questions