Independent policy gradient for large-scale markov potential games: Sharper rates, function approximation, and game-agnostic convergence

D Ding, CY Wei, K Zhang… - … Conference on Machine …, 2022 - proceedings.mlr.press
We examine global non-asymptotic convergence properties of policy gradient methods for
multi-agent reinforcement learning (RL) problems in Markov potential games (MPGs). To …

Breaking the curse of multiagency: Provably efficient decentralized multi-agent rl with function approximation

Y Wang, Q Liu, Y Bai, C Jin - The Thirty Sixth Annual …, 2023 - proceedings.mlr.press
A unique challenge in Multi-Agent Reinforcement Learning (MARL) is the\emph {curse of
multiagency}, where the description length of the game as well as the complexity of many …

Fast policy extragradient methods for competitive games with entropy regularization

S Cen, Y Wei, Y Chi - Advances in Neural Information …, 2021 - proceedings.neurips.cc
This paper investigates the problem of computing the equilibrium of competitive games,
which is often modeled as a constrained saddle-point optimization problem with probability …

Multi-player zero-sum Markov games with networked separable interactions

C Park, K Zhang, A Ozdaglar - Advances in Neural …, 2024 - proceedings.neurips.cc
We study a new class of Markov games,\textit {(multi-player) zero-sum Markov Games} with
{\it Networked separable interactions}(zero-sum NMGs), to model the local interaction …

Breaking the curse of multiagents in a large state space: Rl in markov games with independent linear function approximation

Q Cui, K Zhang, S Du - The Thirty Sixth Annual Conference …, 2023 - proceedings.mlr.press
We propose a new model,\emph {independent linear Markov game}, for multi-agent
reinforcement learning with a large state space and a large number of agents. This is a class …

Interaction-Aware Decision-Making for Autonomous Vehicles

Y Chen, S Li, X Tang, K Yang, D Cao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Complex, dynamic, and interactive environment brings huge challenges to autonomous
driving technologies. Because of the strong interactions between different traffic participants …

Learning in games: a systematic review

RJ Qin, Y Yu - Science China Information Sciences, 2024 - Springer
Game theory studies the mathematical models for self-interested individuals. Nash
equilibrium is arguably the most central solution in game theory. While finding the Nash …

Regret minimization and convergence to equilibria in general-sum markov games

L Erez, T Lancewicki, U Sherman… - International …, 2023 - proceedings.mlr.press
An abundance of recent impossibility results establish that regret minimization in Markov
games with adversarial opponents is both statistically and computationally intractable …

A mean-field game approach to cloud resource management with function approximation

W Mao, H Qiu, C Wang, H Franke… - Advances in …, 2022 - proceedings.neurips.cc
Reinforcement learning (RL) has gained increasing popularity for resource management in
cloud services such as serverless computing. As self-interested users compete for shared …

V-learning—a simple, efficient, decentralized algorithm for multiagent reinforcement learning

C Jin, Q Liu, Y Wang, T Yu - Mathematics of Operations …, 2024 - pubsonline.informs.org
A major challenge of multiagent reinforcement learning (MARL) is the curse of multiagents,
where the size of the joint action space scales exponentially with the number of agents. This …