Offline Meta Reinforcement Learning with In-Distribution Online Adaptation.
Jianhao WangJin ZhangHaozhe JiangJunyu ZhangLiwei WangChongjie ZhangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- online learning
- real time
- state space
- online environment
- spatial distribution
- function approximation
- adaptation process
- probability distribution
- data distribution
- multi agent reinforcement learning
- power law
- uniformly distributed
- temporal difference
- learning algorithm
- optimal policy
- database
- least squares
- case based reasoning
- machine learning
- case study