Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization.
Tiantian ZhangZichuan LinYuxing WangDeheng YeQiang FuWei YangXueqian WangBin LiangBo YuanXiu LiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- adaptive learning
- real time
- state space
- markov decision processes
- information retrieval
- learning algorithm
- reinforcement learning algorithms
- dynamic programming
- optimal control
- robotic control
- autonomous learning
- adaptive control
- dynamic model
- dynamical systems
- optimal policy
- multi agent
- information systems
- search engine