Replay-enhanced Continual Reinforcement Learning.
Tiantian ZhangKevin Zehua ShenZichuan LinBo YuanXueqian WangXiu LiDeheng YePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- control problems
- transfer learning
- optimal policy
- dynamic programming
- learning process
- multi agent
- multi agent reinforcement learning
- real world
- optimal control
- robot control
- learning problems
- robotic control
- control policy
- direct policy search
- reinforcement learning algorithms
- temporal difference
- decision trees
- website
- decision making