Markov Decision Processes with Imprecise Transition Probabilities.
Chelsea C. White IIIHany K. EldeibPublished in: Oper. Res. (1994)
Keyphrases
- markov decision processes
- transition probabilities
- markov chain
- state space
- random walk
- markov models
- finite state
- optimal policy
- policy iteration
- dynamic programming
- reward function
- reinforcement learning
- transition matrices
- partially observable
- maximum entropy
- average reward
- infinite horizon
- hidden variables
- decision theoretic planning
- average cost
- markov decision process
- action space
- markov decision problems
- decision processes
- hidden markov models