Nonstationary zero sum stochastic games with incomplete observation.
D. LeaoJoão Bosco Ribeiro do ValMarcelo D. FragosoPublished in: CDC (2000)
Keyphrases
- stochastic games
- non stationary
- markov decision processes
- nash equilibria
- games with incomplete information
- multiagent reinforcement learning
- multi agent
- reinforcement learning algorithms
- nash equilibrium
- finite horizon
- infinite horizon
- single agent
- optimal policy
- repeated games
- supply chain
- robust optimization
- imperfect information
- learning algorithm