Conjectural Online Learning with First-order Beliefs in Asymmetric Information Stochastic Games.
Tao LiKim HammarRolf StadlerQuanyan ZhuPublished in: CoRR (2024)
Keyphrases
- online learning
- stochastic games
- nash equilibria
- markov decision processes
- multiagent reinforcement learning
- learning strategies
- first order logic
- e learning
- multi agent
- average reward
- belief revision
- active learning
- decision making
- learning automata
- nash equilibrium
- reinforcement learning algorithms
- repeated games
- search algorithm
- markov chain
- robust optimization
- machine learning
- imperfect information
- incomplete information
- state space
- dynamic programming