Learning Stationary Nash Equilibrium Policies in \(n\)-Player Stochastic Games with Independent Chains
From MaRDI portal
Publication:6150987
DOI10.1137/22m1512880arXiv2201.12224OpenAlexW4392355037MaRDI QIDQ6150987
No author found.
Publication date: 7 March 2024
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2201.12224
stochastic gameslearning in gamessmart gridsdual averagingNikaido-Isoda functionstationary Nash equilibriumdual mirror descent
Stochastic games, stochastic differential games (91A15) Algorithmic game theory and complexity (91A68) Equilibrium refinements (91A11)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Zero-sum constrained stochastic games with independent state processes
- Constrained cost-coupled stochastic games with independent state processes
- Learning in games with continuous action sets and unknown payoff functions
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Potential games
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- On the Complexity of Approximating a Nash Equilibrium
- Online Markov Decision Processes Under Bandit Feedback
- Network Security
- Online Markov Decision Processes
- Correlated Equilibrium as an Expression of Bayesian Rationality
- Stochastic Games for the Smart Grid Energy Management With Prospect Prosumers
- Continuous-Time Discounted Mirror Descent Dynamics in Monotone Concave Games
- Fictitious Play in Zero-Sum Stochastic Games
- Bandit Algorithms
- On the convergence of regret minimization dynamics in concave games
- The Complexity of Computing a Nash Equilibrium
- Prediction, Learning, and Games
- Existence and Uniqueness of Equilibrium Points for Concave N-Person Games
- Twenty Lectures on Algorithmic Game Theory
- Stochastic Games
- Unifying mirror descent and dual averaging
