The Role of Diverse Replay for Generalisation in Reinforcement Learning.
Max WeltevredeMatthijs T. J. SpaanWendelin BöhmerPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- wide variety
- machine learning
- multi agent reinforcement learning
- temporal difference
- optimal policy
- learning algorithm
- feature selection
- least squares
- supervised learning
- information systems
- transfer learning
- computer vision
- reinforcement learning algorithms
- learning capabilities
- learning agent
- real world