Reinforcement learning with experience replay and adaptation of action dispersion.
Pawel WawrzynskiWojciech MasarczykMateusz OstaszewskiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- action selection
- partially observable domains
- action space
- adaptation process
- function approximation
- reward shaping
- transition model
- model free
- state action
- adaptation strategies
- reinforcement learning methods
- optimal policy
- learning capabilities
- reinforcement learning algorithms
- state space
- reasoning about actions
- action models
- dynamic programming
- partially observable
- multi agent reinforcement learning
- machine learning