Analysis of an evolutionary reinforcement learning method in a multiagent domain.
Jan Hendrik MetzenMark EdgingtonYohannes KassahunFrank KirchnerPublished in: AAMAS (1) (2008)
Keyphrases
- experimental evaluation
- synthetic data
- reinforcement learning
- dynamic programming
- detection method
- multi agent
- high precision
- learning algorithm
- computational complexity
- preprocessing
- pairwise
- high accuracy
- learning agents
- classification method
- function approximation
- transition model
- multiagent learning
- neural network
- segmentation method
- statistical analysis
- cost function
- significant improvement
- prior knowledge
- similarity measure
- machine learning