Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI Plays Trackmania with Reinforcement Learning
| Date | Stars |
|---|---|
| 2026-07-31 | 739 |
| 2026-08-01 | 739 |
| 2026-08-02 | 739 |
| 2026-08-05 | 739 |
| 2026-08-06 | 739 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <h3>Linesight</h3> Trackmania AI <br> <strong>[Linesight documentation][doc-link]</strong> <br> <br> [![Discord][doc-badge]][doc-link] [![Discord][discord-badge]][discord-link] </div> ## Linesight Linesight is a reinforcement learning project seeking to push what can be done with AI in Trackmania as far as possible. ## Trackmania Trackmania is a racing game that sacrifices some of the realism of sim-racers for a wide variety of track types with all kinds of tricks like wall riding, stunt jumps and wallbangs. Furthermore, Trackmania was designed for equality of input devices which means that keyboard inputs are a viable way to play and therefore that discrete input algorithms like DQN can be applied. In other words, Trackmania is a deep game which can serve as a benchmark to work on any RL algorithm. ## Trackmania Interface Our work, combined with the efforts of [donadigo](https://github.com/donadigo) and [Kim](https://github.com/koyaanis) of the [Trackmania Interface team](https://donadigo.com/tminterface/) allow interfacing to [Trackmania Nations Forever](https://en.wikipedia.org/wiki/TrackMania#TrackMania_United). Allowing you to programmatically send inputs, get car states, get screenshots, etc... This part of our codebase could be useful to other RL projects. ## Results To our knowledge, Linesight is by far the most advanced AI in Trackmania. It was the first to demonstrate human-level driving around May 2023, with [Wirtual playing against it](https://www.youtube.com/watch?v=wjHW3ai47Og) in June. In May 2024, Linesight was the first to [showcase beating world records on official campaign tracks](https://www.youtube.com/watch?v=cUojVsCJ51I). Now that the project is open-source, can you help make it even stronger? [doc-link]: https://linesight-rl.github.io/linesight/build/html/ [discord-link]: https://discord.gg/PvWYGkGKqd [doc-badge]: https://img.shields.io/badge/Documentation-blue?style=for-the-badge&logoSize=small&logo=readthedocs [discord-badge]: https://img.shields.io/discord/847108820479770686?style=for-the-badge&logo=discord&logoSize=auto&label=Discord
Excerpt of 2,156 characters
Read on GitHub
436
Roche Diagnostics
236
29
5
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6f1b2cdbef3be47f, desc:reinforcement learning