Improving Offline Reinforcement Learning with Inaccurate Simulators.
Yiwen HouHaoyuan SunJinming MaFeng WuPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- state space
- real time
- learning agents
- website
- expert systems
- temporal difference learning
- database
- reinforcement learning algorithms
- optimal control
- optimal policy
- markov chain
- supervised learning
- learning process
- data structure
- case study
- artificial intelligence
- learning algorithm