English

Efficient Reinforcement Learning Development with RLzoo

Artificial Intelligence 2021-08-20 v2

Abstract

Many researchers and developers are exploring for adopting Deep Reinforcement Learning (DRL) techniques in their applications. They however often find such an adoption challenging. Existing DRL libraries provide poor support for prototyping DRL agents (i.e., models), customising the agents, and comparing the performance of DRL agents. As a result, the developers often report low efficiency in developing DRL agents. In this paper, we introduce RLzoo, a new DRL library that aims to make the development of DRL agents efficient. RLzoo provides developers with (i) high-level yet flexible APIs for prototyping DRL agents, and further customising the agents for best performance, (ii) a model zoo where users can import a wide range of DRL agents and easily compare their performance, and (iii) an algorithm that can automatically construct DRL agents with custom components (which are critical to improve agent's performance in custom applications). Evaluation results show that RLzoo can effectively reduce the development cost of DRL agents, while achieving comparable performance with existing DRL libraries.

Keywords

Cite

@article{arxiv.2009.08644,
  title  = {Efficient Reinforcement Learning Development with RLzoo},
  author = {Zihan Ding and Tianyang Yu and Yanhua Huang and Hongming Zhang and Guo Li and Quancheng Guo and Luo Mai and Hao Dong},
  journal= {arXiv preprint arXiv:2009.08644},
  year   = {2021}
}

Comments

Accepted by ACM Multimedia Open Source Software Competition

R2 v1 2026-06-23T18:37:54.725Z