Approximate difference rewards for scalable multigent reinforcement learning

We address the problem ofmultiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference...

Full description

Saved in:
Bibliographic Details
Main Authors: SINGH, Arambam James, KUMAR, Akshat, LAU, Hoong Chuin
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6022
https://ink.library.smu.edu.sg/context/sis_research/article/7025/viewcontent/AAMAS_2021_ext_abs.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:We address the problem ofmultiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains - air-traffic control and cooperative navigation, shows better solution quality than previous approaches.