Task decomposition and dynamic policy merging in the distributed Q-learning classifier system.
Kevin L. ChapmanJohn S. BayPublished in: CIRA (1997)
Keyphrases
- cooperative
- multi agent
- optimal policy
- learning algorithm
- action selection
- reinforcement learning
- lightweight
- distributed systems
- dynamic environments
- machine learning
- state space
- path planning
- decision problems
- distributed environment
- function approximation
- communication cost
- mobile robot
- reward function
- stochastic approximation