Salvato in:
Dettagli Bibliografici
Autori principali: Bonnet, Clément, Luo, Daniel, Byrne, Donal, Surana, Shikha, Abramowitz, Sasha, Duckworth, Paul, Coyette, Vincent, Midgley, Laurence I., Tegegn, Elshadai, Kalloniatis, Tristan, Mahjoub, Omayma, Macfarlane, Matthew, Smit, Andries P., Grinsztajn, Nathan, Boige, Raphael, Waters, Cemlyn N., Mimouni, Mohamed A., Sob, Ulrich A. Mbou, de Kock, Ruan, Singh, Siddarth, Furelos-Blanco, Daniel, Le, Victor, Pretorius, Arnu, Laterre, Alexandre
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2306.09884
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911798955868160
author Bonnet, Clément
Luo, Daniel
Byrne, Donal
Surana, Shikha
Abramowitz, Sasha
Duckworth, Paul
Coyette, Vincent
Midgley, Laurence I.
Tegegn, Elshadai
Kalloniatis, Tristan
Mahjoub, Omayma
Macfarlane, Matthew
Smit, Andries P.
Grinsztajn, Nathan
Boige, Raphael
Waters, Cemlyn N.
Mimouni, Mohamed A.
Sob, Ulrich A. Mbou
de Kock, Ruan
Singh, Siddarth
Furelos-Blanco, Daniel
Le, Victor
Pretorius, Arnu
Laterre, Alexandre
author_facet Bonnet, Clément
Luo, Daniel
Byrne, Donal
Surana, Shikha
Abramowitz, Sasha
Duckworth, Paul
Coyette, Vincent
Midgley, Laurence I.
Tegegn, Elshadai
Kalloniatis, Tristan
Mahjoub, Omayma
Macfarlane, Matthew
Smit, Andries P.
Grinsztajn, Nathan
Boige, Raphael
Waters, Cemlyn N.
Mimouni, Mohamed A.
Sob, Ulrich A. Mbou
de Kock, Ruan
Singh, Siddarth
Furelos-Blanco, Daniel
Le, Victor
Pretorius, Arnu
Laterre, Alexandre
contents Open-source reinforcement learning (RL) environments have played a crucial role in driving progress in the development of AI algorithms. In modern RL research, there is a need for simulated environments that are performant, scalable, and modular to enable their utilization in a wider range of potential real-world applications. Therefore, we present Jumanji, a suite of diverse RL environments specifically designed to be fast, flexible, and scalable. Jumanji provides a suite of environments focusing on combinatorial problems frequently encountered in industry, as well as challenging general decision-making tasks. By leveraging the efficiency of JAX and hardware accelerators like GPUs and TPUs, Jumanji enables rapid iteration of research ideas and large-scale experimentation, ultimately empowering more capable agents. Unlike existing RL environment suites, Jumanji is highly customizable, allowing users to tailor the initial state distribution and problem complexity to their needs. Furthermore, we provide actor-critic baselines for each environment, accompanied by preliminary findings on scaling and generalization scenarios. Jumanji aims to set a new standard for speed, adaptability, and scalability of RL environments.
format Preprint
id arxiv_https___arxiv_org_abs_2306_09884
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Bonnet, Clément
Luo, Daniel
Byrne, Donal
Surana, Shikha
Abramowitz, Sasha
Duckworth, Paul
Coyette, Vincent
Midgley, Laurence I.
Tegegn, Elshadai
Kalloniatis, Tristan
Mahjoub, Omayma
Macfarlane, Matthew
Smit, Andries P.
Grinsztajn, Nathan
Boige, Raphael
Waters, Cemlyn N.
Mimouni, Mohamed A.
Sob, Ulrich A. Mbou
de Kock, Ruan
Singh, Siddarth
Furelos-Blanco, Daniel
Le, Victor
Pretorius, Arnu
Laterre, Alexandre
Machine Learning
Artificial Intelligence
Open-source reinforcement learning (RL) environments have played a crucial role in driving progress in the development of AI algorithms. In modern RL research, there is a need for simulated environments that are performant, scalable, and modular to enable their utilization in a wider range of potential real-world applications. Therefore, we present Jumanji, a suite of diverse RL environments specifically designed to be fast, flexible, and scalable. Jumanji provides a suite of environments focusing on combinatorial problems frequently encountered in industry, as well as challenging general decision-making tasks. By leveraging the efficiency of JAX and hardware accelerators like GPUs and TPUs, Jumanji enables rapid iteration of research ideas and large-scale experimentation, ultimately empowering more capable agents. Unlike existing RL environment suites, Jumanji is highly customizable, allowing users to tailor the initial state distribution and problem complexity to their needs. Furthermore, we provide actor-critic baselines for each environment, accompanied by preliminary findings on scaling and generalization scenarios. Jumanji aims to set a new standard for speed, adaptability, and scalability of RL environments.
title Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2306.09884