Nonzero-sum stochastic games with unbounded costs: Discounted and average cost cases.
Linn I. SennottPublished in: Math. Methods Oper. Res. (1994)
Keyphrases
- average cost
- stochastic games
- markov decision processes
- infinite horizon
- average reward
- optimal policy
- long run
- finite horizon
- finite state
- markov decision chains
- reinforcement learning
- reinforcement learning algorithms
- dynamic programming
- state space
- finite number
- policy iteration
- partially observable
- total cost
- optimal control
- initial state
- markov decision process
- nash equilibria
- linear programming
- multistage
- linear program
- supply chain
- imperfect information
- decision making
- probability distribution
- partially observable markov decision processes
- expected cost
- convergence rate