Learning Zero-sum Stochastic Games with Posterior Sampling.
Mehdi Jafarnia-JahromiRahul JainAshutosh NayyarPublished in: CoRR (2021)
Keyphrases
- stochastic games
- nash equilibria
- markov decision processes
- repeated games
- multiagent reinforcement learning
- games with incomplete information
- reinforcement learning algorithms
- average reward
- multi agent
- learning tasks
- supervised learning
- upper bound
- probability distribution
- learning process
- single agent
- fixed point
- knowledge acquisition
- imperfect information