A unified stochastic approximation framework for learning in games

DOI10.1007/s10107-023-02001-yarXiv2206.03922OpenAlexW4310434368MaRDI QIDQ6120942

Ya-Ping Hsieh, Volkan Cevher, Panayotis Mertikopoulos

Publication date: 21 February 2024

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2206.03922

Mathematics Subject Classification ID

Stochastic games, stochastic differential games (91A15) Rationality and learning in game theory (91A26) Algorithmic game theory and complexity (91A68)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Primal-dual subgradient methods for convex problems
• Stochastic uncoupled dynamics and Nash equilibrium
• A modification of the Arrow-Hurwicz method for search of saddle points
• Evolutionary stability in asymmetric games
• Evolutionarily stable strategies and game dynamics
• The weighted majority algorithm
• Vertex-reinforced random walks and a conjecture of Pemantle
• Learning in games with continuous action sets and unknown payoff functions
• Potential games
• Asymptotic pseudotrajectories and chain recurrent flows, with applications
• Generalised weakened fictitious play
• A class of games possessing pure-strategy Nash equilibria
• An iterative method of solving a game
• Learning in Games via Reinforcement and Regularization
• On the Characterization of Local Nash Equilibria in Continuous Games
• Rate control for communication networks: shadow prices, proportional fairness and stability
• Penalty-Regulated Dynamics and Robust Learning Procedures in Games
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Evolutionary game dynamics
• Learning with minimal information in continuous games
• Bandit Algorithms
• Solving variational inequalities with Stochastic Mirror-Prox algorithm
• On the convergence of regret minimization dynamics in concave games
• Learning Generalized Nash Equilibria in a Class of Convex Games
• Individual Q-Learning in Normal Form Games
• The Logic of Animal Conflict
• Prediction, Learning, and Games
• On the Global Convergence of Stochastic Fictitious Play
• Existence and Uniqueness of Equilibrium Points for Concave N-Person Games
• A Social Equilibrium Existence Theorem*
• A Stochastic Approximation Method
• Convex analysis and monotone operator theory in Hilbert spaces