Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhu, Zheqing, Braz, Rodrigo de Salvo, Bhandari, Jalaj, Jiang, Daniel, Wan, Yi, Efroni, Yonathan, Wang, Liyuan, Xu, Ruiyang, Guo, Hongbo, Nikulkov, Alex, Korenkevych, Dmytro, Dogan, Urun, Cheng, Frank, Wu, Zheng, Xu, Wanqiao
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2312.03814
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916376192483328
author Zhu, Zheqing
Braz, Rodrigo de Salvo
Bhandari, Jalaj
Jiang, Daniel
Wan, Yi
Efroni, Yonathan
Wang, Liyuan
Xu, Ruiyang
Guo, Hongbo
Nikulkov, Alex
Korenkevych, Dmytro
Dogan, Urun
Cheng, Frank
Wu, Zheng
Xu, Wanqiao
author_facet Zhu, Zheqing
Braz, Rodrigo de Salvo
Bhandari, Jalaj
Jiang, Daniel
Wan, Yi
Efroni, Yonathan
Wang, Liyuan
Xu, Ruiyang
Guo, Hongbo
Nikulkov, Alex
Korenkevych, Dmytro
Dogan, Urun
Cheng, Frank
Wu, Zheng
Xu, Wanqiao
contents Reinforcement learning (RL) is a versatile framework for optimizing long-term goals. Although many real-world problems can be formalized with RL, learning and deploying a performant RL policy requires a system designed to address several important challenges, including the exploration-exploitation dilemma, partial observability, dynamic action spaces, and safety concerns. While the importance of these challenges has been well recognized, existing open-source RL libraries do not explicitly address them. This paper introduces Pearl, a Production-Ready RL software package designed to embrace these challenges in a modular way. In addition to presenting benchmarking results, we also highlight examples of Pearl's ongoing industry adoption to demonstrate its advantages for production use cases. Pearl is open sourced on GitHub at github.com/facebookresearch/pearl and its official website is pearlagent.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03814
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pearl: A Production-ready Reinforcement Learning Agent
Zhu, Zheqing
Braz, Rodrigo de Salvo
Bhandari, Jalaj
Jiang, Daniel
Wan, Yi
Efroni, Yonathan
Wang, Liyuan
Xu, Ruiyang
Guo, Hongbo
Nikulkov, Alex
Korenkevych, Dmytro
Dogan, Urun
Cheng, Frank
Wu, Zheng
Xu, Wanqiao
Machine Learning
Artificial Intelligence
Reinforcement learning (RL) is a versatile framework for optimizing long-term goals. Although many real-world problems can be formalized with RL, learning and deploying a performant RL policy requires a system designed to address several important challenges, including the exploration-exploitation dilemma, partial observability, dynamic action spaces, and safety concerns. While the importance of these challenges has been well recognized, existing open-source RL libraries do not explicitly address them. This paper introduces Pearl, a Production-Ready RL software package designed to embrace these challenges in a modular way. In addition to presenting benchmarking results, we also highlight examples of Pearl's ongoing industry adoption to demonstrate its advantages for production use cases. Pearl is open sourced on GitHub at github.com/facebookresearch/pearl and its official website is pearlagent.github.io.
title Pearl: A Production-ready Reinforcement Learning Agent
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2312.03814