Optimization of a special case of continuous-time Markov decision processes with compact action set.
Tang HaoZhou LeiArai TamioPublished in: Eur. J. Oper. Res. (2008)
Keyphrases
- markov decision processes
- special case
- state space
- finite state
- decision theoretic planning
- reinforcement learning
- optimal policy
- action space
- markov chain
- linear programming
- dynamic programming
- reinforcement learning algorithms
- factored mdps
- probability distribution
- average cost
- planning under uncertainty
- machine learning
- transition matrices