Dynamic Deep Factor Graph for Multi-Agent Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Yuchen, Duan, Shihong, Xu, Cheng, Wang, Ran, Ye, Fangwen, Yuen, Chau
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911909778817024
author Shi, Yuchen
Duan, Shihong
Xu, Cheng
Wang, Ran
Ye, Fangwen
Yuen, Chau
author_facet Shi, Yuchen
Duan, Shihong
Xu, Cheng
Wang, Ran
Ye, Fangwen
Yuen, Chau
contents This work introduces a novel value decomposition algorithm, termed \textit{Dynamic Deep Factor Graphs} (DDFG). Unlike traditional coordination graphs, DDFG leverages factor graphs to articulate the decomposition of value functions, offering enhanced flexibility and adaptability to complex value function structures. Central to DDFG is a graph structure generation policy that innovatively generates factor graph structures on-the-fly, effectively addressing the dynamic collaboration requirements among agents. DDFG strikes an optimal balance between the computational overhead associated with aggregating value functions and the performance degradation inherent in their complete decomposition. Through the application of the max-sum algorithm, DDFG efficiently identifies optimal policies. We empirically validate DDFG's efficacy in complex scenarios, including higher-order predator-prey tasks and the StarCraft II Multi-agent Challenge (SMAC), thus underscoring its capability to surmount the limitations faced by existing value decomposition algorithms. DDFG emerges as a robust solution for MARL challenges that demand nuanced understanding and facilitation of dynamic agent collaboration. The implementation of DDFG is made publicly accessible, with the source code available at \url{https://github.com/SICC-Group/DDFG}.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05542
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic Deep Factor Graph for Multi-Agent Reinforcement Learning
Shi, Yuchen
Duan, Shihong
Xu, Cheng
Wang, Ran
Ye, Fangwen
Yuen, Chau
Robotics
Multiagent Systems
This work introduces a novel value decomposition algorithm, termed \textit{Dynamic Deep Factor Graphs} (DDFG). Unlike traditional coordination graphs, DDFG leverages factor graphs to articulate the decomposition of value functions, offering enhanced flexibility and adaptability to complex value function structures. Central to DDFG is a graph structure generation policy that innovatively generates factor graph structures on-the-fly, effectively addressing the dynamic collaboration requirements among agents. DDFG strikes an optimal balance between the computational overhead associated with aggregating value functions and the performance degradation inherent in their complete decomposition. Through the application of the max-sum algorithm, DDFG efficiently identifies optimal policies. We empirically validate DDFG's efficacy in complex scenarios, including higher-order predator-prey tasks and the StarCraft II Multi-agent Challenge (SMAC), thus underscoring its capability to surmount the limitations faced by existing value decomposition algorithms. DDFG emerges as a robust solution for MARL challenges that demand nuanced understanding and facilitation of dynamic agent collaboration. The implementation of DDFG is made publicly accessible, with the source code available at \url{https://github.com/SICC-Group/DDFG}.
title Dynamic Deep Factor Graph for Multi-Agent Reinforcement Learning
topic Robotics
Multiagent Systems
url https://arxiv.org/abs/2405.05542