Robustness and sample complexity of model-based MARL for general-sum Markov games

DOI10.1007/S13235-023-00490-2zbMath1519.91030arXiv2110.02355OpenAlexW3204293975MaRDI QIDQ6159508

Amit K. Sinha, Jayakumar Subramanian, Aditya Mahajan

Publication date: 20 June 2023

Published in: Dynamic Games and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.02355

Mathematics Subject Classification ID

Stochastic games, stochastic differential games (91A15) Markov and semi-Markov decision processes (90C40) Algorithmic game theory and complexity (91A68)

Related Items (1)

Special issue: multi-agent dynamic decision making and learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
• Stationary equilibria in stochastic games: structure, selection, and computation
• Lipschitz continuity of value functions in Markovian decision processes
• Homotopy methods to compute equilibria in game theory
• If multi-agent learning is the answer, what is the question?
• Nonlinear programming and stationary equilibria in stochastic games
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• Robust Markov perfect equilibria
• Hilbert space embeddings and metrics on probability measures
• A theory of regular Markov perfect equilibria in dynamic stochastic games: Genericity, stability, and purification
• Sequential Estimation of Dynamic Discrete Games
• Asymptotic Least Squares Estimators for Dynamic Games
• A Theory of Dynamic Oligopoly, I: Overview and Quantity Competition with Large Fixed Costs
• A Theory of Dynamic Oligopoly, II: Price Competition, Kinked Demand Curves, and Edgeworth Cycles
• Representation and Approximation of Noncooperative Sequential Games
• A birth–death model of advertising and pricing
• Integral Probability Metrics and Their Generating Classes of Functions
• Approximations in Dynamic Zero-Sum Games II
• How Does the Value Function of a Markov Decision Process Depend on the Transition Probabilities?
• Markov-Perfect Industry Dynamics: A Framework for Empirical Work
• Approximations in Dynamic Zero-Sum Games I
• Handbook of Dynamic Game Theory
• Estimating Dynamic Models of Imperfect Competition
• Prediction, Learning, and Games
• On Nonterminating Stochastic Games
• Stochastic Games
• \(H^ \infty\)-optimal control and related minimax design problems. A dynamic game approach.
• Markov perfect equilibrium. I: Observable actions

This page was built for publication: Robustness and sample complexity of model-based MARL for general-sum Markov games