Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| 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 |