Reachability for Branching Concurrent Stochastic Games.
Kousha EtessamiEmanuel MartinovAlistair StewartMihalis YannakakisPublished in: ICALP (2019)
Keyphrases
- stochastic games
- markov decision processes
- state space
- nash equilibria
- reinforcement learning algorithms
- games with incomplete information
- multi agent
- multiagent reinforcement learning
- search tree
- nash equilibrium
- learning automata
- single agent
- repeated games
- branch and bound
- average reward
- incomplete information
- optimal policy
- neural network
- long run
- infinite horizon
- game theory
- heuristic search
- cooperative
- knowledge base