A survey of some simulation-based algorithms for Markov decision processes.
Hyeong Soo ChangMichael C. FuJiaqiao HuSteven I. MarcusPublished in: Commun. Inf. Syst. (2007)
Keyphrases
- markov decision processes
- policy iteration
- reinforcement learning
- factored mdps
- state space
- transition matrices
- finite state
- stochastic shortest path
- reachability analysis
- optimal policy
- dynamic programming
- decision theoretic planning
- planning under uncertainty
- policy evaluation
- decision processes
- continuous state spaces
- average cost
- learning algorithm