Rethinking Value Function Learning for Generalization in Reinforcement Learning.
Seungyong MoonJunYeong LeeHyun Oh SongPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- supervised learning
- function approximators
- learning problems
- learning systems
- learning capabilities
- online learning
- autonomous learning
- mobile learning
- active learning
- state space
- transfer learning
- prior knowledge
- multi agent
- state action
- learned knowledge
- learning agents
- temporal difference learning
- reinforcement learning methods
- neural network