A fuzzy approach to Markov decision processes with uncertain transition probabilities.
Masami KuranoMasami YasudaJun-ichi NakagamiYuji YoshidaPublished in: Fuzzy Sets Syst. (2006)
Keyphrases
- markov decision processes
- transition probabilities
- markov chain
- reward function
- state space
- finite state
- markov decision process
- random walk
- markov decision problems
- markov models
- optimal policy
- transition matrices
- reinforcement learning
- policy iteration
- decision theoretic planning
- partially observable
- dynamic programming
- infinite horizon
- action space
- average cost
- decision processes
- average reward
- link structure
- stochastic shortest path
- decision making
- markov model
- hidden variables
- sufficient conditions
- hidden markov models
- bayesian networks