Developing control table for multiple agents using GA-Based Q-learning with neighboring crossover.
Tadahiko MurataYusuke AokiPublished in: IEEE Congress on Evolutionary Computation (2007)
Keyphrases
- multiple agents
- multi agent
- single agent
- genetic algorithm
- genetic algorithm ga
- reinforcement learning
- cooperative
- reward function
- control system
- multi agent coordination
- evolutionary algorithm
- database
- learning algorithm
- genetic programming
- function approximation
- control method
- action selection
- fitness function
- simulated annealing
- multi agent systems
- control problems
- control strategy
- crossover operator
- selection strategy
- control strategies
- multiagent systems
- preference elicitation
- agent societies