Mean-Variance Tradeoffs in an Undiscounted MDP: The Unichain Case.
Kun-Jen ChungPublished in: Oper. Res. (1994)
Keyphrases
- finite state
- markov decision processes
- average cost
- initial state
- optimal policy
- policy iteration
- markov decision process
- infinite horizon
- stationary policies
- utility function
- state space
- average reward
- stochastic games
- markov chain
- reinforcement learning
- markov decision problems
- linear programming
- planning under uncertainty
- design decisions
- fixed point
- linear program
- multistage
- dynamic programming