Policy Learning based on Deep Koopman Representation.
Wenjian HaoPaulo C. HerediaBowen HuangZehui LuZihao LiangShaoshuai MouPublished in: CoRR (2023)
Keyphrases
- learning tasks
- learning algorithm
- prior knowledge
- online learning
- reinforcement learning
- inductive inference
- incremental learning
- perceptual information
- genetic algorithm
- multiple representations
- partially observable
- feature representation
- mobile learning
- image representation
- knowledge acquisition
- state space
- learning process
- decision making
- feature selection