wouldn´t a uberbug from second last cp jump into last cp be faster? by like hitting the top of the cp downwards back onto the road. Maybe even nosebug setup from cp bounce down idk

Are you from poland? Czy jesteś z Polski?

Can you make that for tm2020?

Link got this lol

Zajebiste!

I have come to collect your cheese taxes. 10 pieces will do

my best ever is 5.85 lol

You should try to do this using the new trackmania potentially.

It would be cool to implement this in a club on tm2020 maybe with someway of giving feedback on flow

Link has a 27.50

Link destroyed an old tas run thats crazy

Watching the video at 2x speed is the greatest form of music

you speak really good english for someone whose first language is not english, but when you talk about how something looks, you don't say HOW something looks LIKE you say WHAT it looks LIKE. if you say HOW you never end the phrase with LIKE. great vid <33

Pozdrawiam

3:33 Riolu: 0% legit how the tables have turned

Bro trackmania turbo did it in 2016

gen 9 was random

Who else is here because of wirtuals comments on Fall - 18???

this man is a living legend

So this is how lolsport builds his maps...

Can't wait for the spider to be added in Trackmania

AI Gen 1-8: Learning... Learning... AI Gen 9: Fuck it, booster.

As a software engineer and TM fan - this is one of my favorite TM videos to date! GG

I did it this way, not as clean because this is using TAS, but I got a 9.22 with it. Definitely can be optimized and mastered.

Is there any way to use the patch with porting kit for mac? I don't see the (competition patch) in the window title

How has this video not blown up yet :O

This could be a fine addition to a duel 1v1 gamemode where you compete to be the fastest lap by 3 rounds race in a random generated map. Great work dude

Your going to make Trackmania a scientific playground for yourself... Wondering what's next

wow

Some of you may know, I even held a cup with 30 AI generated maps two months back. Here are the results - kzbin.info/www/bejne/fXOvlWypp8trqJo

Omfg! Great work dude!

Well done! Very interesting to watch. Even though it would take much more computing time, wouldn't it make more sense, to get a probability by looking at segments of blocks? Like always 4 blocks at a time for example. Give it a start block. Now calculate a segment of 4 blocks, place the first of them. Now you have two blocks. Calculate first, second, and a theoretical third and fourth (judging by common 4 block patterns, with a start block attatched to the front of them). Place your third block. Now calculate your fourth block, by looking at common 4-block-combinations using the last 2 placed blocks. Place your 4th block. As far as I'm not missjudging it, the endresult should be smoother (even if you don't take the one with the highest probability, cause this would end in the same route every time).

Pls do more of these type of videos! they are so fun to watch!

3:29 “0% legit” ok riolu

you’re a legend

Not real

What's the rationale behind randomly choosing outputs (weighted by probability) rather than choosing the most probable output every time? I can imagine choosing randomly would give more "natural" results in some sense, but would expect overall higher quality tracks from choosing the most probable since results would resemble the training set more closely. Just guessing though, I have little experience working with NNs.

gościu nie tryharduj tak bo ci żyła pierdolnie

Some of these generated maps look like kacky maps

Do u know how to fix game not compatible?

how did you iterate from generation to generation ? how do you give a score to a track ?

could this not be a good start for creating a ai that can identify possible stolen tracks?

wicked'

Nice Kacky map generator you've got there ;)

how does this work can we also run this within trackmania to generate our own maps?

Why are we not using reinforcement learning or particle swarm based algorithms to create theoretical speedruns with AI? I kept looking for it and there are some initial works on it but with a legend like Donadigo on board, we might come up with AI speedruns.

awesome video! Now combine that with @Yosh 's TM driver AI to drive AI generated tracks. That way we have completely eliminated the human in the process and fully bowed down to our robot overlords.

So so cool ! greatjob An idea : maybe you could provide your neural network with a sense of the driving flow by providing it with the trajectory of a player for each block of the track (or at least, player's entry point & speed and exit point & speed for each of the block) Maybe with this kind of training data, the network would learn the correlation between common sequences of blocks and the expected trajectory and speed on those sequences ?

Crazy, u are like the engineer of the community, u are giving us a lot, thank you and keep up the work

11:59 Did the AI put a big jump at the end of the boosts, to try to get the car out of the stadium? That's what all new players do the first time they try the map editor ahah, Nice video !