MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Felten, Florian, Ucak, Umut, Azmani, Hicham, Peng, Gao, Röpke, Willem, Baier, Hendrik, Mannion, Patrick, Roijers, Diederik M., Terry, Jordan K., Talbi, El-Ghazali, Danoy, Grégoire, Nowé, Ann, Rădulescu, Roxana
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916456580513792
author Felten, Florian
Ucak, Umut
Azmani, Hicham
Peng, Gao
Röpke, Willem
Baier, Hendrik
Mannion, Patrick
Roijers, Diederik M.
Terry, Jordan K.
Talbi, El-Ghazali
Danoy, Grégoire
Nowé, Ann
Rădulescu, Roxana
author_facet Felten, Florian
Ucak, Umut
Azmani, Hicham
Peng, Gao
Röpke, Willem
Baier, Hendrik
Mannion, Patrick
Roijers, Diederik M.
Terry, Jordan K.
Talbi, El-Ghazali
Danoy, Grégoire
Nowé, Ann
Rădulescu, Roxana
contents Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitating progress, evaluation, and reproducibility. The significance of benchmarks is underscored by the existence of numerous benchmark frameworks developed for various RL paradigms, including single-agent RL (e.g., Gymnasium), multi-agent RL (e.g., PettingZoo), and single-agent multi-objective RL (e.g., MO-Gymnasium). To support the advancement of the MOMARL field, we introduce MOMAland, the first collection of standardised environments for multi-objective multi-agent reinforcement learning. MOMAland addresses the need for comprehensive benchmarking in this emerging field, offering over 10 diverse environments that vary in the number of agents, state representations, reward structures, and utility considerations. To provide strong baselines for future research, MOMAland also includes algorithms capable of learning policies in such settings.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16312
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning
Felten, Florian
Ucak, Umut
Azmani, Hicham
Peng, Gao
Röpke, Willem
Baier, Hendrik
Mannion, Patrick
Roijers, Diederik M.
Terry, Jordan K.
Talbi, El-Ghazali
Danoy, Grégoire
Nowé, Ann
Rădulescu, Roxana
Multiagent Systems
Artificial Intelligence
Computer Science and Game Theory
Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitating progress, evaluation, and reproducibility. The significance of benchmarks is underscored by the existence of numerous benchmark frameworks developed for various RL paradigms, including single-agent RL (e.g., Gymnasium), multi-agent RL (e.g., PettingZoo), and single-agent multi-objective RL (e.g., MO-Gymnasium). To support the advancement of the MOMARL field, we introduce MOMAland, the first collection of standardised environments for multi-objective multi-agent reinforcement learning. MOMAland addresses the need for comprehensive benchmarking in this emerging field, offering over 10 diverse environments that vary in the number of agents, state representations, reward structures, and utility considerations. To provide strong baselines for future research, MOMAland also includes algorithms capable of learning policies in such settings.
title MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning
topic Multiagent Systems
Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2407.16312