HackerTube.dev

Training an unbeatable AI in Trackmania

Yosh · 17.7M views · 2023-09-30 · 20:41

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

Yosh trains a reinforcement learning agent to drive Trackmania until he can no longer beat it. The video explains how the training works and the design choices involved.

On Hacker News

Recommended as an approachable explanation of how reinforcement learning works in practice, and cited for the constraints needed to stop exploits.

Recommended by 1 HN people across 1 months · HN mentions 2024–2025

Topics

Machine learning & deep learningGaming culture & analysis
Search by tags
trackmaniareinforcement learninggame aimachine learningtminterface

What people said

smokel · 2024-07 · Strong recommendation

For those who only read the comments, be sure to check out the videos by Yosh. They're amazing, and do a great job explaining how reinforcement learning works in practice: [VIDEO] [LINK]

Read the original HN comment ↗
szvsw · 2025-02 · Reference

There’s a few very cool examples where someone recently used RL to solve trackmania, and ends up having to add all sorts of constraints/penalties to prevent extremely strange exploits/glitches that are discovered IIRC… been a while since I watched. [VIDEO] [LINK]

Read the original HN comment ↗
fragmede · 2024-10 · Reference

Depends what you consider fun, and how far you take it. Some people enjoy programming more than repetitive clicking in a GUI. For a clicker game, writing a bot lets you iterate on strategies easier - is it faster to get to level 2 if I buy the upgrade for A or B first? For Trackmania, it lets you get a world record and a YouTube video with 14M views. [VIDEO]

Read the original HN comment ↗

Sources

Video by Yosh, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Topic keywords do not match
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources