MDPs with setwise continuous transition probabilities.
Eugene A. FeinbergPavlo O. KasyanovPublished in: Oper. Res. Lett. (2021)
Keyphrases
- transition probabilities
- markov chain
- markov decision problems
- random walk
- markov models
- markov decision process
- reward function
- state space
- markov decision processes
- link structure
- hidden variables
- optimal policy
- bayesian networks
- maximum entropy
- markov model
- text mining
- collaborative filtering
- information extraction