Multiagent coordination utilising Q-learning.
Srikanta PatnaikNitaigour-Premchand MahalikPublished in: Int. J. Autom. Control. (2007)
Keyphrases
- multiagent coordination
- reinforcement learning
- function approximation
- state space
- cooperative
- multi agent
- learning algorithm
- action selection
- model free
- reinforcement learning algorithms
- optimal policy
- learning rate
- stochastic approximation
- multi agent reinforcement learning
- policy iteration
- learning agent
- temporal difference learning
- dynamic programming
- search space
- expert systems
- decision making
- neural network
- stochastic shortest path