A Weighted Markov Decision Process.
Dmitry KrassJerzy A. FilarSagnik S. SinhaPublished in: Oper. Res. (1992)
Keyphrases
- markov decision process
- state space
- optimal policy
- reinforcement learning
- markov decision processes
- temporal difference learning
- finite horizon
- infinite horizon
- transition matrices
- initial state
- reward function
- partial observability
- average cost
- decision problems
- dynamic programming
- policy iteration
- hidden markov models
- bayesian networks
- machine learning