Zero-sum stochastic games with unbounded costs: Discounted and average cost cases.
Linn I. SennottPublished in: Math. Methods Oper. Res. (1994)
Keyphrases
- stochastic games
- average cost
- markov decision processes
- infinite horizon
- average reward
- long run
- optimal policy
- finite horizon
- finite state
- games with incomplete information
- reinforcement learning algorithms
- multiagent reinforcement learning
- reinforcement learning
- policy iteration
- state space
- dynamic programming
- optimal control
- initial state
- repeated games
- partially observable
- multistage
- nash equilibria
- stationary policies
- finite number
- learning automata
- linear program
- machine learning
- total cost