Application of Markov decision processes to search problems.
Leo B. HartmanKees M. van HeePublished in: Decis. Support Syst. (1995)
Keyphrases
- markov decision processes
- search problems
- optimal policy
- finite state
- transition matrices
- dynamic programming
- state space
- reinforcement learning
- decision theoretic planning
- orders of magnitude
- heuristic search
- policy iteration
- search algorithm
- reachability analysis
- action sets
- infinite horizon
- average cost
- partially observable
- planning under uncertainty
- computational complexity
- search space
- evolutionary algorithm