Copertina

Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Leonardos, Stefanos, Overman, Will, Panageas, Ioannis, Piliouras, Georgios
Natura:	Preprint
Pubblicazione:	2021
Soggetti:	Machine Learning Computer Science and Game Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization
di: Daskalakis, Constantinos, et al.
Pubblicazione: (2018)

Convergence of Regret Matching in Potential Games and Constrained Optimization
di: Anagnostides, Ioannis, et al.
Pubblicazione: (2025)

Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games
di: Feng, Yi, et al.
Pubblicazione: (2024)

Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria
di: Barakat, Anas, et al.
Pubblicazione: (2026)

Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play
di: Lazarsfeld, John, et al.
Pubblicazione: (2025)

Provable Policy Gradient Methods for Average-Reward Markov Potential Games
di: Cheng, Min, et al.
Pubblicazione: (2024)

Optimism Without Regularization: Constant Regret in Zero-Sum Games
di: Lazarsfeld, John, et al.
Pubblicazione: (2025)

Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games
di: Dong, Jing, et al.
Pubblicazione: (2024)

Solving Zero-Sum Convex Markov Games
di: Kalogiannis, Fivos, et al.
Pubblicazione: (2025)

Faster Rates for No-Regret Learning in General Games via Cautious Optimism
di: Soleymani, Ashkan, et al.
Pubblicazione: (2025)

Data-Scarce Identification of Game Dynamics via Sum-of-Squares Optimization
di: Sakos, Iosif, et al.
Pubblicazione: (2023)

Online Multi-Agent Control with Adversarial Disturbances
di: Barakat, Anas, et al.
Pubblicazione: (2025)

Cautious Optimism: A Meta-Algorithm for Near-Constant Regret in General Games
di: Soleymani, Ashkan, et al.
Pubblicazione: (2025)

Deep Incentive Design with Differentiable Equilibrium Blocks
di: Thoma, Vinzenz, et al.
Pubblicazione: (2026)

Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
di: Kalogiannis, Fivos, et al.
Pubblicazione: (2024)

(Doubly) Exponential Lower Bounds for Follow the Regularized Leader in Potential Games
di: Anagnostides, Ioannis, et al.
Pubblicazione: (2026)

Swim till You Sink: Computing the Limit of a Game
di: Hakim, Rashida, et al.
Pubblicazione: (2024)

Polynomial Convergence of Bandit No-Regret Dynamics in Congestion Games
di: Dadi, Leello, et al.
Pubblicazione: (2024)

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
di: Lei, Qi, et al.
Pubblicazione: (2020)

Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
di: Maiti, Arnab, et al.
Pubblicazione: (2026)

When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
di: Lazarsfeld, John, et al.
Pubblicazione: (2026)

Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning
di: Gemp, Ian, et al.
Pubblicazione: (2024)

Computing Nash Equilibria in Potential Games with Private Uncoupled Constraints
di: Patris, Nikolas, et al.
Pubblicazione: (2024)

Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
di: Zhang, Brian Hu, et al.
Pubblicazione: (2025)

A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence
di: Liu, Mingyang, et al.
Pubblicazione: (2024)

Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players
di: Alatur, Pragnya, et al.
Pubblicazione: (2024)

Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees
di: Chen, Ziqin, et al.
Pubblicazione: (2026)

Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg
di: Feng, Yi, et al.
Pubblicazione: (2024)

Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
di: Park, Chanwoo, et al.
Pubblicazione: (2023)

Independent Learning in Constrained Markov Potential Games
di: Jordan, Philip, et al.
Pubblicazione: (2024)

Regret Minimization and Convergence to Equilibria in General-sum Markov Games
di: Erez, Liad, et al.
Pubblicazione: (2022)

The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
di: Anagnostides, Ioannis, et al.
Pubblicazione: (2025)

Scale-Invariant Fast Convergence in Games
di: Tsuchiya, Taira, et al.
Pubblicazione: (2026)

Playing Markov Games Without Observing Payoffs
di: Ablin, Daniel, et al.
Pubblicazione: (2025)

Tight Inapproximability for Welfare-Maximizing Autobidding Equilibria
di: Anagnostides, Ioannis, et al.
Pubblicazione: (2026)

Chaos in Autobidding Auctions
di: Anagnostides, Ioannis, et al.
Pubblicazione: (2026)

Efficient Kernelized Learning in Polyhedral Games Beyond Full-Information: From Colonel Blotto to Congestion Games
di: Kontogiannis, Andreas, et al.
Pubblicazione: (2025)

Re-evaluating Open-ended Evaluation of Large Language Models
di: Liu, Siqi, et al.
Pubblicazione: (2025)

Cooperative Game-Theoretic Credit Assignment for Multi-Agent Policy Gradients via the Core
di: Ji, Mengda, et al.
Pubblicazione: (2025)

Computational Lower Bounds for Regret Minimization in Normal-Form Games
di: Anagnostides, Ioannis, et al.
Pubblicazione: (2024)