Markov Decision Processes with a Borel Measurable Cost Function - The Average Case.
Masami KuranoPublished in: Math. Oper. Res. (1986)
Keyphrases
- average case
- markov decision processes
- cost function
- worst case
- state space
- finite state
- optimal policy
- uniform distribution
- reinforcement learning
- transition matrices
- dynamic programming
- objective function
- policy iteration
- average cost
- markov decision process
- infinite horizon
- partially observable
- action space
- expected cost
- upper bound
- average reward
- decision theoretic planning
- sufficient conditions
- semi supervised