Distributed TD Tracking with Linear Function Approximation over Directed Communication Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Haocheng, Zhao, Shengchao, Liu, Yongchao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914533715476480
author Yang, Haocheng
Zhao, Shengchao
Liu, Yongchao
author_facet Yang, Haocheng
Zhao, Shengchao
Liu, Yongchao
contents We study the policy evaluation problem in multi-agent reinforcement learning (MARL) over directed communication networks, where agents cooperate with each other to explore an unknown environment and accomplish a specific task. We propose a Push-Pull-type distributed algorithm, named PP-DTD, for policy evaluation in MARL within the framework of temporal difference (TD) learning with linear function approximation. PP-DTD integrates TD learning with the Push-Pull mechanism to accommodate directed communication networks, and further utilizes variance reduction techniques to enhance both algorithmic stability and convergence rate. We show that PP-DTD achieves linear convergence to a neighborhood of the optimum under constant step-sizes and a convergence rate of $\mathcal{O}({T^{-1}})$ under decaying step-sizes when the sample is independent and identically distributed or Markovian. To the best of our knowledge, PP-DTD is the first distributed algorithm for policy evaluation in MARL over directed graphs that achieves a comparable convergence rate to single-agent TD. The numerical experiments on cooperative navigation tasks demonstrate the robustness and effectiveness of PP-DTD.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04466
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Distributed TD Tracking with Linear Function Approximation over Directed Communication Networks
Yang, Haocheng
Zhao, Shengchao
Liu, Yongchao
Optimization and Control
We study the policy evaluation problem in multi-agent reinforcement learning (MARL) over directed communication networks, where agents cooperate with each other to explore an unknown environment and accomplish a specific task. We propose a Push-Pull-type distributed algorithm, named PP-DTD, for policy evaluation in MARL within the framework of temporal difference (TD) learning with linear function approximation. PP-DTD integrates TD learning with the Push-Pull mechanism to accommodate directed communication networks, and further utilizes variance reduction techniques to enhance both algorithmic stability and convergence rate. We show that PP-DTD achieves linear convergence to a neighborhood of the optimum under constant step-sizes and a convergence rate of $\mathcal{O}({T^{-1}})$ under decaying step-sizes when the sample is independent and identically distributed or Markovian. To the best of our knowledge, PP-DTD is the first distributed algorithm for policy evaluation in MARL over directed graphs that achieves a comparable convergence rate to single-agent TD. The numerical experiments on cooperative navigation tasks demonstrate the robustness and effectiveness of PP-DTD.
title Distributed TD Tracking with Linear Function Approximation over Directed Communication Networks
topic Optimization and Control
url https://arxiv.org/abs/2605.04466