Bayesian Learning of Noisy Markov Decision Processes.
Sumeetpal S. SinghNicolas ChopinNick WhiteleyPublished in: ACM Trans. Model. Comput. Simul. (2013)
Keyphrases
- markov decision processes
- bayesian learning
- model selection
- reinforcement learning
- optimal policy
- finite state
- policy iteration
- transition matrices
- state space
- dynamic programming
- posterior distribution
- average reward
- incomplete data
- decision theoretic planning
- infinite horizon
- average cost
- markov decision process
- missing data
- hidden markov models
- search space
- training data