On Average Reward Semi-Markov Decision Processes with a General Multichain Structure.
Jianyong LiuXiaobo ZhaoPublished in: Math. Oper. Res. (2004)
Keyphrases
- average reward
- semi markov decision processes
- markov decision processes
- long run
- optimal policy
- reinforcement learning
- optimality criterion
- model free
- markov chain
- policy iteration
- special case
- discounted reward
- state space
- dynamic programming
- knowledge base
- supply chain
- data mining
- search space
- infinite horizon
- markov decision process
- machine learning