Guardado en:
Detalles Bibliográficos
Autores principales: Farebrother, Jesse, Castro, Pablo Samuel
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.23810
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913568960544768
author Farebrother, Jesse
Castro, Pablo Samuel
author_facet Farebrother, Jesse
Castro, Pablo Samuel
contents We introduce the Continuous Arcade Learning Environment (CALE), an extension of the well-known Arcade Learning Environment (ALE) [Bellemare et al., 2013]. The CALE uses the same underlying emulator of the Atari 2600 gaming system (Stella), but adds support for continuous actions. This enables the benchmarking and evaluation of continuous-control agents (such as PPO [Schulman et al., 2017] and SAC [Haarnoja et al., 2018]) and value-based agents (such as DQN [Mnih et al., 2015] and Rainbow [Hessel et al., 2018]) on the same environment suite. We provide a series of open questions and research directions that CALE enables, as well as initial baseline results using Soft Actor-Critic. CALE is available as part of the ALE athttps://github.com/Farama-Foundation/Arcade-Learning-Environment.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23810
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CALE: Continuous Arcade Learning Environment
Farebrother, Jesse
Castro, Pablo Samuel
Machine Learning
Artificial Intelligence
We introduce the Continuous Arcade Learning Environment (CALE), an extension of the well-known Arcade Learning Environment (ALE) [Bellemare et al., 2013]. The CALE uses the same underlying emulator of the Atari 2600 gaming system (Stella), but adds support for continuous actions. This enables the benchmarking and evaluation of continuous-control agents (such as PPO [Schulman et al., 2017] and SAC [Haarnoja et al., 2018]) and value-based agents (such as DQN [Mnih et al., 2015] and Rainbow [Hessel et al., 2018]) on the same environment suite. We provide a series of open questions and research directions that CALE enables, as well as initial baseline results using Soft Actor-Critic. CALE is available as part of the ALE athttps://github.com/Farama-Foundation/Arcade-Learning-Environment.
title CALE: Continuous Arcade Learning Environment
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.23810