Learning to Utilize Curiosity: A New Approach of Automatic Curriculum Learning for Deep RL
In recent years, reinforcement learning algorithms based on automatic curriculum learning have been increasingly applied to multi-agent system problems. However, in the sparse reward environment, the reinforcement learning agents get almost no feedback from the environment during the whole training...
Main Authors: | Zeyang Lin, Jun Lai, Xiliang Chen, Lei Cao, Jun Wang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/10/14/2523 |
Similar Items
-
Autonomous Maneuver Decision-Making Through Curriculum Learning and Reinforcement Learning With Sparse Rewards
by: Yujie Wei, et al.
Published: (2023-01-01) -
Curriculum Reinforcement Learning Based on K-Fold Cross Validation
by: Zeyang Lin, et al.
Published: (2022-12-01) -
Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning
by: Xuecheng Niu, et al.
Published: (2024-01-01) -
Maneuver Decision-Making through Automatic Curriculum Reinforcement Learning without Handcrafted Reward Functions
by: Yujie Wei, et al.
Published: (2023-08-01) -
Learning robotic manipulation skills with multiple semantic goals by conservative curiosity-motivated exploration
by: Changlin Han, et al.
Published: (2023-03-01)