SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.02682 · 2019

Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multi-agent reinforcement learning (MARL) has recently received considerable attention due to its applicability to a wide range of real-world applications. However, achieving efficient communication among agents has always been an overarching problem in MARL. In this work, we propose Variance Based Control (VBC), a simple yet efficient technique to improve communication efficiency in MARL. By limiting the variance of the exchanged messages between agents during the training phase, the noisy component in the messages can be eliminated effectively, while the useful part can be preserved and utilized by the agents for better performance. Our evaluation using a challenging set of StarCraft II benchmarks indicates that our method achieves $2-10\times$ lower in communication overhead than state-of-the-art MARL algorithms, while allowing agents to better collaborate by developing sophisticated strategies.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1909.02682")
get_code_for_paper("1909.02682")
have("1909.02682")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1909.02682.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1909.02682.svg)](https://syntology.ai/paper/1909.02682)

Connect an agent — have() is free.