A statistical property of multiagent learning based on Markov decision process.
Kazunori IwataKazushi IkedaHideaki SakaiPublished in: IEEE Trans. Neural Networks (2006)
Keyphrases
- markov decision process
- multiagent learning
- reinforcement learning
- optimal policy
- state space
- multi agent
- markov decision processes
- infinite horizon
- multiagent systems
- state action
- resource allocation
- temporal difference learning
- policy iteration
- initial state
- action space
- game theoretic
- multi agent learning
- machine learning
- nash equilibria
- search algorithm