JORLDY: a fully customizable open source framework for reinforcement learning

TL;DR

JORLDY is an open-source, highly customizable reinforcement learning framework supporting over 20 algorithms and multiple environments, designed to facilitate research and education in RL.

Contribution

It introduces a flexible, PyTorch-based RL framework with extensive algorithm and environment support, tailored for researchers and students.

Findings

Supports over 20 RL algorithms with easy customization

Compatible with multiple RL environments including OpenAI gym and Unity ML-Agents

Facilitates RL research and education through open-source availability

Abstract

Recently, Reinforcement Learning (RL) has been actively researched in both academic and industrial fields. However, there exist only a few RL frameworks which are developed for researchers or students who want to study RL. In response, we propose an open-source RL framework "Join Our Reinforcement Learning framework for Developing Yours" (JORLDY). JORLDY provides more than 20 widely used RL algorithms which are implemented with Pytorch. Also, JORLDY supports multiple RL environments which include OpenAI gym, Unity ML-Agents, Mujoco, Super Mario Bros and Procgen. Moreover, the algorithmic components such as agent, network, environment can be freely customized, so that the users can easily modify and append algorithmic components. We expect that JORLDY will support various RL research and contribute further advance the field of RL. The source code of JORLDY is provided on the following Github: https://github.com/kakaoenterprise/JORLDY