A Case Study on Stochastic Games on Large Graphs in Mean Field and Sparse Regimes.
Daniel LackerAgathe SoretPublished in: Math. Oper. Res. (2022)
Keyphrases
- stochastic games
- nash equilibria
- markov decision processes
- multiagent reinforcement learning
- infinite horizon
- learning automata
- markov random field
- repeated games
- nash equilibrium
- em algorithm
- reinforcement learning algorithms
- robust optimization
- imperfect information
- single agent
- markov networks
- belief networks
- search algorithm
- average reward
- reinforcement learning
- monte carlo
- learning agent
- cooperative
- incomplete information
- multi agent