Fictitious Play in Zero-Sum Stochastic Games
From MaRDI portal
Publication:5093269
DOI10.1137/21M1426675zbMath1497.91031arXiv2010.04223OpenAlexW3092557414MaRDI QIDQ5093269
Asuman Ozdaglar, Francesca Parise, Muhammed O. Sayin
Publication date: 26 July 2022
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2010.04223
Learning and adaptive systems in artificial intelligence (68T05) 2-person games (91A05) Stochastic games, stochastic differential games (91A15)
Related Items
Affine Relaxations of the Best Response Algorithm: Global Convergence in Ratio-Bounded Games, Learning Stationary Nash Equilibrium Policies in \(n\)-Player Stochastic Games with Independent Chains, Decentralized inertial best-response with voluntary and limited communication in random communication networks
Cites Work
- Fictitious play applied to sequences of games and discounted stochastic games
- Asynchronous stochastic approximation and Q-learning
- On the rate of convergence of continuous-time fictitious play
- \({\mathcal Q}\)-learning
- A \(2 \times 2\) game without the fictitious play property
- Learning in extensive-form games. I: Self-confirming equilibria
- Fictitious play property for games with identical interests
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Best-response dynamics in zero-sum stochastic games
- Fictitious play in stochastic games
- Generalised weakened fictitious play
- An iterative method of solving a game
- 10.1162/153244303765208377
- Evolution equations in discrete and continuous time for nonexpansive operators in Banach spaces
- On Best-Response Dynamics in Potential Games
- REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES
- Robustness Properties in Fictitious-Play-Type Algorithms
- Bandit Algorithms
- Payoff-Based Dynamics for Multiplayer Weakly Acyclic Games
- Decentralized Q-Learning for Stochastic Teams and Games
- Stochastic Approximations and Differential Inclusions
- Individual Q-Learning in Normal Form Games
- Stochastic Games
- Real and functional analysis
- Nash equilibrium and the evolution of preferences
