Symbol generation and feature selection for reinforcement learning agents using affordances and U-Trees.
Marcus Carlos OladellManfred HuberPublished in: SMC (2012)
Keyphrases
- reinforcement learning agents
- feature selection
- symbol recognition
- reinforcement learning
- dynamic environments
- decision trees
- multi agent
- text categorization
- state abstraction
- machine learning
- feature space
- transfer learning
- genetic algorithm
- pairwise
- text classification
- compact representations
- state space
- learning algorithm