Overtaking Optimality for Markov Decision Chains.
Eric V. DenardoUriel G. RothblumPublished in: Math. Oper. Res. (1979)
Keyphrases
- markov decision chains
- average cost
- long run
- markov decision processes
- finite state
- finite number
- optimal control
- optimal policy
- infinite horizon
- linear program
- risk sensitive
- multistage
- linear programming
- finite horizon
- optimal solution
- total cost
- reinforcement learning
- least squares
- state space
- search space
- markov decision process
- markov decision problems
- multi agent