Deep Multi-agent Reinforcement Learning in a Homogeneous Open Population

Roxana Rădulescu*, Manon Legrand, Kyriakos Efthymiadis, Diederik M. Roijers, Ann Nowé

*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Advances in reinforcement learning research have recently produced agents that are competent, or sometimes exceed human performance, in complex tasks. Most interesting real world problems however, are not restricted to one agent, but instead deal with multiple agents acting in the same environment and have proven to be challenging tasks to solve. In this work we present a study on a homogeneous open population of agents modelled as a multi-agent reinforcement learning (MARL) system. We propose a centralised learning approach, with decentralised execution in which agents are given the same policy to execute individually. Using the SimuLane highway traffic simulator as a test-bed we show experimentally that using a single-agent learnt policy to initialise the multi-agent scenario, which we then fine-tune to the task, out-performs agents that learn in the multi-agent setting from scratch. Specifically we contribute an open population MARL configuration, how to transfer knowledge from single- to a multi-agent setting and a training procedure for a homogeneous open population of agents.

Original languageEnglish
Title of host publicationARTIFICIAL INTELLIGENCE
Subtitle of host publication30th Benelux Conference, BNAIC 2018, Den Bosch November 8-9 2018, Revised Selected Papers
EditorsMartin Atzmueller, Wouter Duivesteijn
PublisherSpringer
Pages90-105
Number of pages16
ISBN (Electronic)9783030319786
ISBN (Print)9783030319779
DOIs
Publication statusPublished - 2019
Event30th Benelux Conference on Artificial Intelligence, BNAIC 2018 - ‘s-Hertogenbosch, Netherlands
Duration: 8 Nov 20189 Nov 2018

Publication series

NameCommunications in Computer and Information Science
Volume1021
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference30th Benelux Conference on Artificial Intelligence, BNAIC 2018
CountryNetherlands
City‘s-Hertogenbosch
Period8/11/189/11/18

Keywords

  • Highway traffic
  • Multi-agent systems
  • Open population
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Deep Multi-agent Reinforcement Learning in a Homogeneous Open Population'. Together they form a unique fingerprint.

Cite this