A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent.
Mehdi Jafarnia-JahromiRahul A. JainAshutosh NayyarPublished in: AISTATS (2024)
Keyphrases
- stochastic games
- learning algorithm
- imperfect information
- reinforcement learning algorithms
- learning agent
- games with incomplete information
- reinforcement learning
- markov decision processes
- nash equilibria
- repeated games
- nash equilibrium
- model free
- multiagent reinforcement learning
- state space
- active learning
- average reward
- multi agent
- single agent
- machine learning algorithms
- learning process
- learning automata
- game theoretic
- function approximation
- learning tasks
- reward function
- machine learning
- supervised learning
- perfect information
- computational complexity
- genetic algorithm