I trained an AI in Trackmania with reinforcement learning, and tried to make it learn the hardest technique in this game: the noseboost. To support my work on Patreon: • Note: This video was re-uploaded a few hours after the original upluoad due to a copyright issue with the music Contact • Discord: yosh_tm • Twitter:  yoshtm1   • Mail: @ Link to download the last map: TAS runs shown in the video: A01-Race, by igntul & Lukalyc: A09-Race, by gingerroar & plastorex: D12-Speed, by threadd: Other reinforcement learning projects mentioned in the video: GT Sophy: OpenAI Five: RLGym: Linesight: @linesight-rl Thanks to Donadigo, for TMInterface! The setup used in all maps to put the car on its nose was inspired by this map: On a more general note, this video would not have been possible without the passion and creativity of the TAS community, who discovered the noseboost in 2021. Special thanks to them :) More information on Trackmania TAS here: You can find a list of the musics I used at the end of the video.