Offline Reinforcement Learning with Reverse Model-based Imagination.
Jianhao WangWenzhe LiHaozhe JiangGuangxiang ZhuSiyuan LiChongjie ZhangPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- model free
- function approximation
- temporal difference
- control problems
- real time
- reinforcement learning algorithms
- state space
- learning process
- information systems
- machine learning
- artificial intelligence
- learning algorithm
- data driven
- markov decision processes
- data mining
- temporal difference learning
- action space
- human intelligence
- reinforcement learning methods
- relational reinforcement learning
- robotic control
- learning classifier systems
- evaluation function
- multi agent systems
- multi agent
- genetic algorithm
- information retrieval
- real world