Yosh
AI just Broke Trackmanias Greatest World Record
updated
Between research, programming and editing, these videos take a long time to produce. Any support on Patreon will help me to spend more time on that in the future :)
• Patreon : patreon.com/Yoshtm
Contact
• Discord: yosh_tm
• Twitter: yoshtm1
• Mail: yoshtm.yt@gmail.com
The maps shown in this video can be downloaded on TMX and played in Trackmania Nations Forever:
• 1) One Hella Long Pipe (It requires TMUnlimiter !) - https://tmnf.exchange/trackshow/8484272
• 2) Calm Down - https://tmnf.exchange/trackshow/1293088
• 3) Are You Serious ?! - https://tmnf.exchange/trackshow/5152869
Wirtual made a nice video about his world record on the track Calm Down, don’t hesitate to watch it : youtube.com/watch?v=x-uEI6zQCi0
More generally, if you want to learn more about this game, check out his streams and videos, he makes fantastic content !
• twitch.tv/wirtual
• youtube.com/@Wirtual
You can find a list of the musics I used at the end of the video. Special thanks to Beik Poel for allowing me to use their song En aften ved svanefossen : youtube.com/watch?v=KBl-QdasurU
Thanks to Donadigo, for TMInterface !
donadigo.com/tminterface
All Trackmania Nations Forever tricks TIERLIST – Fliks.
youtube.com/watch?v=jokU_OtO9Q0
Into The Breach vs. Karmine Corp | Semifinal 2 | World Championship 2023 – Trackmania World Tour
youtube.com/watch?v=MOyBM867Yes
I just opened a Patreon page, where you can support this YouTube channel with a donation (link below). Between research, programming and editing, these videos take a long time to produce. Any support will help me to spend more time on that in the future ! This one in particular took up most of my time over the last six months. I hope you like the result, and I'm open to any feedback to improve the quality of these videos :) I'll post more details on the Patreon page to explain what I plan to do next.
• Patreon : patreon.com/Yoshtm
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 : http://files.trackmaniaforever.com/tmnationsforever_setup.exe
• TMInfinity: unlimiter.net/download
• Download the maps on TMX : https://tmnf.exchange/tracksearch?query=author%3a+yoshtm
Contact
• Discord : yosh_tm
• Twitter : twitter.com/yoshtm1
Special thanks to Donadigo, for TMInterface !
Again, a big thanks to Donadigo for TMInterface !
Contact :
Discord – yosh_tm
Twitter – twitter.com/yoshtm1
Thanks to everyone who sent me a replay on the second map !
Contact :
Discord – yosh_tm
Twitter – twitter.com/yoshtm1
__________________________
__________________________
Some more details about the supervised learning part : I'm playing with a keyboard, and A.I. learns to predict which keys I will press for a given set of inputs. I'm recording "Left" and "Right" as 0 (no press) or 1 (press). A.I. uses a joystick, so it needs to predict a single direction value between 0.0 and 1.0. So, for each set of inputs, its neural network predicts the probabilty that I would turn left and the probability that I would turn right. And A.I. uses the highest probabilty to know in which direction it should turn, and with what intensity.
Contact :
Discord – yosh_tm
Twitter – twitter.com/yoshtm1
Music : youtube.com/watch?v=yfkI4i0Rz2g
Thanks Trabadia ! His Youtube channel : youtube.com/user/Trabadia1
More information about NEAT algorithm :
neat-python.readthedocs.io/en/latest/neat_overview.html
Contact :
Discord – yosh_tm
Twitter – twitter.com/yoshtm1
Some more details about the AI :
I'm using artificial neural network, a machine-learning algorithm. The network has 16 inputs (15 wall distances + speed) and 4 outputs (forward, backward, left, right). The model in this video has 2 hidden layers (64 + 16 neurons). I tried other configurations and it didn’t change much. In Trackmania² stadium, I used image analysis to retrieve the speed value in the bottom right corner of the screen. It’s not possible anymore in the new game. Instead, I'm using Openplanet to access directly the game’s API. This way, I can get other data such as gear. I tried to add this additional information as input data of the model, but it doesn’t improve the AI.
I recorded 50.000 data lines in order to train the model. For each frame, I can use its mirrored version to double the amount of data. So I used 100.000 data records in total (90.000 for training + 10.000 for validation).
My program captures about 13 frames per second.
Thanks to the Openplanet community for the help ! (https://openplanet.nl/)
Contact :
Discord - yosh_tm
Twitter - twitter.com/yoshtm1
Music :
1) Airtone - Forgottenland
2) Meydän - Synthwave Vibe
3) His Boy Elroy - Revolve
I'm using artificial neural network, a machine-learning algorithm. The network has 16 inputs (15 wall distances + speed) and 4 outputs (forward, backward, left, right). The model in this video has 2 hidden layers (64 + 16 neurons). I’ll try to improve it in the future.
I hope the voice recording isn’t too bad quality. Any feedback is welcome !
Contact :
Discord - yosh_tm
Twitter - twitter.com/yoshtm1
Music :
1) Phone Call – Jon Brion (extended version)
2) Forever – Martin Garrix, Matisse & Sadko
I tried something a bit different : generally, on this type of video, replays are driven one by one by some players. Here, replays are also driven one by one, but everything was done automatically. I wrote a script that drives automatically a replay on a map, then saves it, then starts again, etc. Each replay is driven with random inputs. It took 50h of automatic driving in total.
Hope you like the final result ;)
Contact :
Discord - yosh_tm
Twitter - twitter.com/yoshtm1
Music :
1) In The Hall Of The Mountain King (PD Arrangement) - Trent Reznor, Atticus Ross
2) Les Ramoneurs de menhirs- Dañs Gwadek 1


