Model-Based Reinforcement Learning for Alternating Markov Games.
Drew MellorPublished in: Australian Conference on Artificial Intelligence (2003)
Keyphrases
- model based reinforcement learning
- markov games
- markov decision processes
- reinforcement learning
- finite state
- reinforcement learning algorithms
- optimal policy
- state space
- dynamic programming
- markov decision process
- decision processes
- multiagent reinforcement learning
- average cost
- infinite horizon
- policy iteration
- stochastic games
- action space
- learning algorithm
- supervised learning
- model free
- incomplete information
- sufficient conditions