A toolkit for reliable benchmarking and ...
Document type :
Communication dans un congrès avec actes
Title :
A toolkit for reliable benchmarking and research in multi-objective reinforcement learning
Author(s) :
Felten, Florian [Auteur]
Université du Luxembourg = University of Luxembourg = Universität Luxemburg [uni.lu]
Lucas Nunes, Alegre [Auteur]
Federal University of Rio Grande do Sul [UFRGS]
Ann, Nowe [Auteur]
Artificial Intelligence Lab [Brussels] [VUB]
Ana L. C., Bazzan [Auteur]
Federal University of Rio Grande do Sul [UFRGS]
El Ghazali, Talbi [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Université de Lille
Inria Lille - Nord Europe
Optimisation de grande taille et calcul large échelle [BONUS]
Grégoire, Danoy [Auteur]
Université du Luxembourg = University of Luxembourg = Universität Luxemburg [uni.lu]
Bruno Castro Da, Silva [Auteur]
University of Massachusetts [Amherst] [UMass Amherst]
Université du Luxembourg = University of Luxembourg = Universität Luxemburg [uni.lu]
Lucas Nunes, Alegre [Auteur]
Federal University of Rio Grande do Sul [UFRGS]
Ann, Nowe [Auteur]
Artificial Intelligence Lab [Brussels] [VUB]
Ana L. C., Bazzan [Auteur]
Federal University of Rio Grande do Sul [UFRGS]
El Ghazali, Talbi [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Université de Lille
Inria Lille - Nord Europe
Optimisation de grande taille et calcul large échelle [BONUS]
Grégoire, Danoy [Auteur]
Université du Luxembourg = University of Luxembourg = Universität Luxemburg [uni.lu]
Bruno Castro Da, Silva [Auteur]
University of Massachusetts [Amherst] [UMass Amherst]
Conference title :
NeuriPS'2023 Thirty-seventh Annual Conference on Neural Information Processing Systems
City :
New Orleans (LA)
Country :
Etats-Unis d'Amérique
Start date of the conference :
2023-12
HAL domain(s) :
Informatique [cs]
English abstract : [en]
Multi-objective reinforcement learning algorithms (MORL) extend standard reinforcement learning (RL) to scenarios where agents must optimize multiple---potentially conflicting---objectives, each represented by a distinct ...
Show more >Multi-objective reinforcement learning algorithms (MORL) extend standard reinforcement learning (RL) to scenarios where agents must optimize multiple---potentially conflicting---objectives, each represented by a distinct reward function. To facilitate and accelerate research and benchmarking in multi-objective RL problems, we introduce a comprehensive collection of software libraries that includes: (i) MO-Gymnasium, an easy-to-use and flexible API enabling the rapid construction of novel MORL environments. It also includes more than 20 environments under this API. This allows researchers to effortlessly evaluate any algorithms on any existing domains; (ii) MORL-Baselines, a collection of reliable and efficient implementations of state-of-the-art MORL algorithms, designed to provide a solid foundation for advancing research. Notably, all algorithms are inherently compatible with MO-Gymnasium; and (iii) a thorough and robust set of benchmark results and comparisons of MORL-Baselines algorithms, tested across various challenging MO-Gymnasium environments. These benchmarks were constructed to serve as guidelines for the research community, underscoring the properties, advantages, and limitations of each particular state-of-the-art method.Show less >
Show more >Multi-objective reinforcement learning algorithms (MORL) extend standard reinforcement learning (RL) to scenarios where agents must optimize multiple---potentially conflicting---objectives, each represented by a distinct reward function. To facilitate and accelerate research and benchmarking in multi-objective RL problems, we introduce a comprehensive collection of software libraries that includes: (i) MO-Gymnasium, an easy-to-use and flexible API enabling the rapid construction of novel MORL environments. It also includes more than 20 environments under this API. This allows researchers to effortlessly evaluate any algorithms on any existing domains; (ii) MORL-Baselines, a collection of reliable and efficient implementations of state-of-the-art MORL algorithms, designed to provide a solid foundation for advancing research. Notably, all algorithms are inherently compatible with MO-Gymnasium; and (iii) a thorough and robust set of benchmark results and comparisons of MORL-Baselines algorithms, tested across various challenging MO-Gymnasium environments. These benchmarks were constructed to serve as guidelines for the research community, underscoring the properties, advantages, and limitations of each particular state-of-the-art method.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :