Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games.
Hédi HadijiSarah SachsTim van ErvenWouter M. KoolenPublished in: CoRR (2023)
Keyphrases
- nash equilibria
- stochastic games
- game theory
- incomplete information
- nash equilibrium
- multiagent learning
- fictitious play
- solution concepts
- learning algorithm
- query complexity
- markov decision processes
- learning process
- learning tasks
- game theoretic
- reinforcement learning
- pure strategy
- first order logic
- multi agent
- learning problems
- utility function
- machine learning
- mixed strategy