Partial-Observation Stochastic Games: How to Win when Belief Fails.
Krishnendu ChatterjeeLaurent DoyenPublished in: ACM Trans. Comput. Log. (2014)
Keyphrases
- stochastic games
- nash equilibria
- markov decision processes
- multiagent reinforcement learning
- nash equilibrium
- multi agent
- repeated games
- reinforcement learning algorithms
- robust optimization
- average reward
- belief revision
- belief functions
- imperfect information
- expected utility
- infinite horizon
- single agent
- long run
- learning automata
- search space