A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jiang, Haozhe, Cui, Qiwen, Xiong, Zhihan, Fazel, Maryam, Du, Simon S.
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911863817633792
author Jiang, Haozhe
Cui, Qiwen
Xiong, Zhihan
Fazel, Maryam
Du, Simon S.
author_facet Jiang, Haozhe
Cui, Qiwen
Xiong, Zhihan
Fazel, Maryam
Du, Simon S.
contents We investigate learning the equilibria in non-stationary multi-agent systems and address the challenges that differentiate multi-agent learning from single-agent learning. Specifically, we focus on games with bandit feedback, where testing an equilibrium can result in substantial regret even when the gap to be tested is small, and the existence of multiple optimal solutions (equilibria) in stationary games poses extra challenges. To overcome these obstacles, we propose a versatile black-box approach applicable to a broad spectrum of problems, such as general-sum games, potential games, and Markov games, when equipped with appropriate learning and testing oracles for stationary environments. Our algorithms can achieve $\widetilde{O}\left(Δ^{1/4}T^{3/4}\right)$ regret when the degree of nonstationarity, as measured by total variation $Δ$, is known, and $\widetilde{O}\left(Δ^{1/5}T^{4/5}\right)$ regret when $Δ$ is unknown, where $T$ is the number of rounds. Meanwhile, our algorithm inherits the favorable dependence on number of agents from the oracles. As a side contribution that may be independent of interest, we show how to test for various types of equilibria by a black-box reduction to single-agent learning, which includes Nash equilibria, correlated equilibria, and coarse correlated equilibria.
format Preprint
id arxiv_https___arxiv_org_abs_2306_07465
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
Jiang, Haozhe
Cui, Qiwen
Xiong, Zhihan
Fazel, Maryam
Du, Simon S.
Machine Learning
Artificial Intelligence
Computer Science and Game Theory
Multiagent Systems
We investigate learning the equilibria in non-stationary multi-agent systems and address the challenges that differentiate multi-agent learning from single-agent learning. Specifically, we focus on games with bandit feedback, where testing an equilibrium can result in substantial regret even when the gap to be tested is small, and the existence of multiple optimal solutions (equilibria) in stationary games poses extra challenges. To overcome these obstacles, we propose a versatile black-box approach applicable to a broad spectrum of problems, such as general-sum games, potential games, and Markov games, when equipped with appropriate learning and testing oracles for stationary environments. Our algorithms can achieve $\widetilde{O}\left(Δ^{1/4}T^{3/4}\right)$ regret when the degree of nonstationarity, as measured by total variation $Δ$, is known, and $\widetilde{O}\left(Δ^{1/5}T^{4/5}\right)$ regret when $Δ$ is unknown, where $T$ is the number of rounds. Meanwhile, our algorithm inherits the favorable dependence on number of agents from the oracles. As a side contribution that may be independent of interest, we show how to test for various types of equilibria by a black-box reduction to single-agent learning, which includes Nash equilibria, correlated equilibria, and coarse correlated equilibria.
title A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Computer Science and Game Theory
Multiagent Systems
url https://arxiv.org/abs/2306.07465