#trackmania#reinforcementlearning#tminterface
424K subscribers • 1 video on Hallway
Intermediate. Assumes working knowledge.
17M views3 years ago1 recommendation
AI and machine learningGame developmentReinforcement learningGame programming
Yosh explains how he trained a reinforcement learning agent to drive Trackmania and the design choices involved in preventing exploits.
I trained an AI in Trackmania with reinforcement learning, until I couldn't beat it. Join my Patreon: patreon.com/Yoshtm There’s also a membership option directly on YouTube: youtube.com/channel/UCh1zLfuN6F_X4eoNKCsyICA/join Contact: • Mail: yoshtm.yt@gmail.com • Discord: yosh_tm • Twitter: yoshtm1 Most of the music I use is from Epidemic Sound: share.epidemicsound.com/13vf27 (affiliate link) Special thanks to Donadigo, for TMInterface ! ______________________________________________________________ If you want to try these maps, you first need to have both Trackmania Nations Forever (TMNF) and TMInfinity installed. Then, you can download the maps on Trackmania Exchange (TMX). Everything is free, and you can use the links below. • TMNF : files.trackmaniaforever.com/tmnationsforever_setup.exe • TMInfinity: unlimiter.net/download • Download the maps on TMX : tmnf.exchange/tracksearch?query=author%3a+yoshtmWhat people say. Recommended as an amazing and practical explanation of how reinforcement learning works in a real-world gaming environment.
smokelon Hacker News • Recommends
On “The History of Machine Learning in Trackmania”
emporason Hacker News • Mentions
On “Chess-GPT's Internal World Model”
fragmedeon Hacker News • Mentions
On “OmniParser for Pure Vision Based GUI Agent”
szvswon Hacker News • Mentions
On “AI-designed chips are so weird that 'humans cannot understand them'”