Bounds and Transformations for Discounted Finite Markov Decision Chains.
Evan L. PorteusPublished in: Oper. Res. (1975)
Keyphrases
- markov decision chains
- average cost
- finite number
- markov decision processes
- stationary policies
- risk sensitive
- infinite horizon
- long run
- finite horizon
- finite state
- upper bound
- state and action spaces
- lower bound
- optimal policy
- discounted reward
- total cost
- optimal control
- multistage
- linear program
- special case
- policy iteration
- sufficient conditions
- state space
- real valued functions
- control system