Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts.
Patrik HammersborgInga StrümkePublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- cognitive map
- robot behavior
- artificial intelligence
- function approximation
- evaluation function
- real time
- concept learning
- physical world
- reinforcement learning algorithms
- learning algorithm
- state space
- dynamic environments
- learning environment
- action selection
- temporal difference
- human operators
- real robot
- e learning