Deciding Maxmin Reachability in Half-Blind Stochastic Games.
Edon KelmendiHugo GimbertPublished in: CoRR (2016)
Keyphrases
- stochastic games
- nash equilibria
- markov decision processes
- games with incomplete information
- state space
- multiagent reinforcement learning
- learning automata
- reinforcement learning algorithms
- nash equilibrium
- multi agent
- repeated games
- robust optimization
- infinite horizon
- incomplete information
- expert systems
- average reward
- worst case
- lower bound
- multi agent systems
- knowledge base