Standard

Deep Multi-Agent Reinforcement Learning in a Homogeneous Open Population. / Radulescu, Roxana; Legrand, Manon; Efthymiadis, Kyriakos; Roijers, Diederik; Nowe, Ann.

Artificial Intelligence: 30th Benelux Conference, BNAIC 2018, ‘s-Hertogenbosch, The Netherlands, November 8–9, 2018, Revised Selected Papers. ed. / Martin Atzmueller; Wouter Duivesteijn. Springer International Publishing, 2019. p. 90-105 (Communications in Computer and Information Science; Vol. 1021).

Research output: Chapter in Book/Report/Conference proceedingConference paper

Harvard

Radulescu, R, Legrand, M, Efthymiadis, K, Roijers, D & Nowe, A 2019, Deep Multi-Agent Reinforcement Learning in a Homogeneous Open Population. in M Atzmueller & W Duivesteijn (eds), Artificial Intelligence: 30th Benelux Conference, BNAIC 2018, ‘s-Hertogenbosch, The Netherlands, November 8–9, 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 1021, Springer International Publishing, pp. 90-105, 30th Benelux Conference on Artificial Intelligence, ‘s-Hertogenbosch, Netherlands, 8/11/18. https://doi.org/10.1007/978-3-030-31978-6_8

APA

Radulescu, R., Legrand, M., Efthymiadis, K., Roijers, D., & Nowe, A. (2019). Deep Multi-Agent Reinforcement Learning in a Homogeneous Open Population. In M. Atzmueller, & W. Duivesteijn (Eds.), Artificial Intelligence: 30th Benelux Conference, BNAIC 2018, ‘s-Hertogenbosch, The Netherlands, November 8–9, 2018, Revised Selected Papers (pp. 90-105). (Communications in Computer and Information Science; Vol. 1021). Springer International Publishing. https://doi.org/10.1007/978-3-030-31978-6_8

Vancouver

Radulescu R, Legrand M, Efthymiadis K, Roijers D, Nowe A. Deep Multi-Agent Reinforcement Learning in a Homogeneous Open Population. In Atzmueller M, Duivesteijn W, editors, Artificial Intelligence: 30th Benelux Conference, BNAIC 2018, ‘s-Hertogenbosch, The Netherlands, November 8–9, 2018, Revised Selected Papers. Springer International Publishing. 2019. p. 90-105. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-030-31978-6_8

Author

Radulescu, Roxana ; Legrand, Manon ; Efthymiadis, Kyriakos ; Roijers, Diederik ; Nowe, Ann. / Deep Multi-Agent Reinforcement Learning in a Homogeneous Open Population. Artificial Intelligence: 30th Benelux Conference, BNAIC 2018, ‘s-Hertogenbosch, The Netherlands, November 8–9, 2018, Revised Selected Papers. editor / Martin Atzmueller ; Wouter Duivesteijn. Springer International Publishing, 2019. pp. 90-105 (Communications in Computer and Information Science).

BibTeX

@inproceedings{6d52b9b6ca3a4ee2b8442b0af78ed933,
title = "Deep Multi-Agent Reinforcement Learning in a Homogeneous Open Population",
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.",
author = "Roxana Radulescu and Manon Legrand and Kyriakos Efthymiadis and Diederik Roijers and Ann Nowe",
year = "2019",
month = "9",
day = "25",
doi = "https://doi.org/10.1007/978-3-030-31978-6_8",
language = "English",
isbn = "978-3-030-31977-9",
series = "Communications in Computer and Information Science",
publisher = "Springer International Publishing",
pages = "90--105",
editor = "Martin Atzmueller and Wouter Duivesteijn",
booktitle = "Artificial Intelligence",

}

RIS

TY - GEN

T1 - Deep Multi-Agent Reinforcement Learning in a Homogeneous Open Population

AU - Radulescu, Roxana

AU - Legrand, Manon

AU - Efthymiadis, Kyriakos

AU - Roijers, Diederik

AU - Nowe, Ann

PY - 2019/9/25

Y1 - 2019/9/25

N2 - 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.

AB - 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.

U2 - https://doi.org/10.1007/978-3-030-31978-6_8

DO - https://doi.org/10.1007/978-3-030-31978-6_8

M3 - Conference paper

SN - 978-3-030-31977-9

T3 - Communications in Computer and Information Science

SP - 90

EP - 105

BT - Artificial Intelligence

A2 - Atzmueller, Martin

A2 - Duivesteijn, Wouter

PB - Springer International Publishing

ER -

ID: 47660263