Home Projects RoboLeague
RoboLeague
C#

RoboLeague

A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.

by roboserg · GitHub
Stars
Forks
Created
Last commit
Category
Language
car-physicsdeep-reinforcement-learningmlagentC#
View on GitHub
In plain words

Experiment with a car soccer game environment designed for training AI in competitive scenarios.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
RoboLeague — GitHub preview card
📈 Star history
308307
2026-07-202026-08-31
📈 Track RoboLeague

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.

RoboLeague has 307 stars on GitHub. It has been forked 20 times. RoboLeague is written mainly in C#. It has been in active development since 2020. Its main topics are car-physics, deep-reinforcement-learning, mlagent, mlagents.

Frequently asked questions

What is RoboLeague?

A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.

Is RoboLeague open source?

RoboLeague is an open-source project.

Is RoboLeague free?

Yes. RoboLeague is free and open source — you can use, modify and self-host it.

What language is RoboLeague written in?

RoboLeague is written mainly in C#.

🏅 Maintainer of this project?
olud.ai badge — RoboLeague

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=roboserg-roboleague)](https://olud.ai/project/roboserg-roboleague.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.