Yiqiu Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yiqiu Hu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
Jun Zhu
School of Computer Science and Technology, East China Normal University, Shanghai, China
1 shared publication- Wenyan Liu
Ant Group, Hangzhou 310023, China
1 shared publication - Yun Hua
East China Normal University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 20 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 67259-67267
Reward Shaping Based Federated Reinforcement Learning
Federated reinforcement learning aims to promote training efficiency or improve policy quality through information interaction with privacy protection. Existing federated reinforcement learning methods rarely utilize the structure of reinforcement learning algorithms while are limiting to specific scenarios or algorithms. We propose a general federated reinforcement learning framework FRS, which employs reward shaping as the federated information shared among different clients with different tasks to promote each client’s training speed and policy quality. The federated reward shaping is implicitly learned by average state value information of all clients to protect each client’s task privacy as the real trajectory is anonymous. Experiments on the GridWorld environment show that FRS can algorithm-independently improve the policy quality and promote training speed with protecting each client’s privacy.
- 20 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 67259-67267
Open AccessReward Shaping Based Federated Reinforcement Learning
Federated reinforcement learning aims to promote training efficiency or improve policy quality through information interaction with privacy protection. Existing federated reinforcement learning methods rarely utilize the structure of reinforcement learning algorithms while are limiting to specific scenarios or algorithms. We propose a general federated reinforcement learning framework FRS, which employs reward shaping as the federated information shared among different clients with different tasks to promote each client’s training speed and policy quality. The federated reward shaping is implicitly learned by average state value information of all clients to protect each client’s task privacy as the real trajectory is anonymous. Experiments on the GridWorld environment show that FRS can algorithm-independently improve the policy quality and promote training speed with protecting each client’s privacy.