Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Linqi, Li, Rankun, Hu, Xiaowen, Li, Jiayi, Xing, Boyang, Peng, Yan, Liang, Bin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929746105860096
author Ye, Linqi
Li, Rankun
Hu, Xiaowen
Li, Jiayi
Xing, Boyang
Peng, Yan
Liang, Bin
author_facet Ye, Linqi
Li, Rankun
Hu, Xiaowen
Li, Jiayi
Xing, Boyang
Peng, Yan
Liang, Bin
contents This paper introduces Unity RL Playground, an open-source reinforcement learning framework built on top of Unity ML-Agents. Unity RL Playground automates the process of training mobile robots to perform various locomotion tasks such as walking, running, and jumping in simulation, with the potential for seamless transfer to real hardware. Key features include one-click training for imported robot models, universal compatibility with diverse robot configurations, multi-mode motion learning capabilities, and extreme performance testing to aid in robot design optimization and morphological evolution. The attached video can be found at https://linqi-ye.github.io/video/iros25.mp4 and the code is coming soon.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05146
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots
Ye, Linqi
Li, Rankun
Hu, Xiaowen
Li, Jiayi
Xing, Boyang
Peng, Yan
Liang, Bin
Robotics
Machine Learning
This paper introduces Unity RL Playground, an open-source reinforcement learning framework built on top of Unity ML-Agents. Unity RL Playground automates the process of training mobile robots to perform various locomotion tasks such as walking, running, and jumping in simulation, with the potential for seamless transfer to real hardware. Key features include one-click training for imported robot models, universal compatibility with diverse robot configurations, multi-mode motion learning capabilities, and extreme performance testing to aid in robot design optimization and morphological evolution. The attached video can be found at https://linqi-ye.github.io/video/iros25.mp4 and the code is coming soon.
title Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots
topic Robotics
Machine Learning
url https://arxiv.org/abs/2503.05146