Standard

A Domain-Specific Language for Multi-Agent Reinforcement Learning in Distributed Systems. / Molderez, Tim Christiaan; Oeyen, Bjarno; De Meuter, Wolfgang.

Benelux Conference on Artificial Intelligence. Vol. 1 BNAIC 2018, Belgium-Netherlands conference on Artificial Intelligence, 2018. p. 169-170.

Research output: Chapter in Book/Report/Conference proceedingMeeting abstract (Book)

Harvard

Molderez, TC, Oeyen, B & De Meuter, W 2018, A Domain-Specific Language for Multi-Agent Reinforcement Learning in Distributed Systems. in Benelux Conference on Artificial Intelligence. vol. 1, BNAIC 2018, Belgium-Netherlands conference on Artificial Intelligence, pp. 169-170, 30th Benelux Conference on Artificial Intelligence - BNAIC 2018, ‘s-Hertogenbosch, Netherlands, 8/11/18.

APA

Molderez, T. C., Oeyen, B., & De Meuter, W. (2018). A Domain-Specific Language for Multi-Agent Reinforcement Learning in Distributed Systems. In Benelux Conference on Artificial Intelligence (Vol. 1, pp. 169-170). BNAIC 2018, Belgium-Netherlands conference on Artificial Intelligence.

Vancouver

Molderez TC, Oeyen B, De Meuter W. A Domain-Specific Language for Multi-Agent Reinforcement Learning in Distributed Systems. In Benelux Conference on Artificial Intelligence. Vol. 1. BNAIC 2018, Belgium-Netherlands conference on Artificial Intelligence. 2018. p. 169-170

Author

Molderez, Tim Christiaan ; Oeyen, Bjarno ; De Meuter, Wolfgang. / A Domain-Specific Language for Multi-Agent Reinforcement Learning in Distributed Systems. Benelux Conference on Artificial Intelligence. Vol. 1 BNAIC 2018, Belgium-Netherlands conference on Artificial Intelligence, 2018. pp. 169-170

BibTeX

@inbook{ae23e14f72d340b587991c6dab64b369,
title = "A Domain-Specific Language for Multi-Agent Reinforcement Learning in Distributed Systems",
abstract = "Many multi-agent reinforcement learning (MARL) problems are well-suited to be solved in a distributed manner. Not only to achieve scalability in terms of runtime or memory, but also because the environment may be a distributed system. While distributed machine learning is appealing in these cases, it does introduce several complexities inherent to distributed computing This paper presents Marlon, a domain-specific language to facilitate MARL in a distributed environment. Marlon essentially acts as a bridge between the environment and the agents observing it, and abstracts away many of the concerns related to distributed computing. We demonstrate Marlon by means of a load balancing example, where MARL is used to optimize the system’s performance, while allowing network nodes to join and leave the system.",
keywords = "Domain-Specific Languages, Multi-agent Reinforcement Learning, Distributed Systems",
author = "Molderez, {Tim Christiaan} and Bjarno Oeyen and {De Meuter}, Wolfgang",
year = "2018",
language = "English",
volume = "1",
pages = "169--170",
booktitle = "Benelux Conference on Artificial Intelligence",
publisher = "BNAIC 2018, Belgium-Netherlands conference on Artificial Intelligence",

}

RIS

TY - CHAP

T1 - A Domain-Specific Language for Multi-Agent Reinforcement Learning in Distributed Systems

AU - Molderez, Tim Christiaan

AU - Oeyen, Bjarno

AU - De Meuter, Wolfgang

PY - 2018

Y1 - 2018

N2 - Many multi-agent reinforcement learning (MARL) problems are well-suited to be solved in a distributed manner. Not only to achieve scalability in terms of runtime or memory, but also because the environment may be a distributed system. While distributed machine learning is appealing in these cases, it does introduce several complexities inherent to distributed computing This paper presents Marlon, a domain-specific language to facilitate MARL in a distributed environment. Marlon essentially acts as a bridge between the environment and the agents observing it, and abstracts away many of the concerns related to distributed computing. We demonstrate Marlon by means of a load balancing example, where MARL is used to optimize the system’s performance, while allowing network nodes to join and leave the system.

AB - Many multi-agent reinforcement learning (MARL) problems are well-suited to be solved in a distributed manner. Not only to achieve scalability in terms of runtime or memory, but also because the environment may be a distributed system. While distributed machine learning is appealing in these cases, it does introduce several complexities inherent to distributed computing This paper presents Marlon, a domain-specific language to facilitate MARL in a distributed environment. Marlon essentially acts as a bridge between the environment and the agents observing it, and abstracts away many of the concerns related to distributed computing. We demonstrate Marlon by means of a load balancing example, where MARL is used to optimize the system’s performance, while allowing network nodes to join and leave the system.

KW - Domain-Specific Languages

KW - Multi-agent Reinforcement Learning

KW - Distributed Systems

M3 - Meeting abstract (Book)

VL - 1

SP - 169

EP - 170

BT - Benelux Conference on Artificial Intelligence

PB - BNAIC 2018, Belgium-Netherlands conference on Artificial Intelligence

ER -

ID: 40239092