quote
@culleng.1653
23/10/01 22:02 
 poparcie   34707
Widz, komentarz do filmu
Showing the AI's multiple training runs simultaneously and color coded is one of the most gorgeous and elegant depictions of machine learning I've ever seen. Thank you for th...
Przejdź do KOMENTARZY POD FILMEM

Komentarze widzów

@culleng.1653 @culleng.1653  23/10/01 22:02  polubiono  34707

Showing the AI's multiple training runs simultaneously and color coded is one of the most gorgeous and elegant depictions of machine learning I've ever seen. Thank you for this video!!

@One_Stale_Donut @One_Stale_Donut  23/09/30 19:26  polubiono  17370

Insane production value, the editing that went into this, and the time it must have taken.

@florrex4136 @florrex4136  23/11/22 11:11  polubiono  4948

That drift-overtraining and then training off the excess is a really interesting approach to let the Ai discover new mechanics👍🏻

@rafaelnubile @rafaelnubile  23/11/19 23:21  polubiono  2946

Now we want a race between programmers to see who makes the fastest AI!

@Ell355ar @Ell355ar  23/10/01 09:43  polubiono  1921

Looking forward to seeing the AI take a shot at Deep Fear one day

@darkranger116 @darkranger116  23/10/01 16:55  polubiono  1748

I always love these training AI videos. Its like the "wizard knows his apprentice will be more powerful than him one day, but only if he is guided there" vibe

@plebiain @plebiain  23/09/30 21:45  polubiono  1538

I would unironically watch hours of you facing off against this AI on different maps to see what it does, please make more!

@lenovoleader @lenovoleader  23/10/08 05:24  polubiono  1422

this the channels that really need to be awarded for the amount of hard work put in

@kevineina6454 @kevineina6454  23/10/14 18:55  polubiono  1398

This project is still (I followed it for a long time) one of the most interesting projects of YouTube. It is indeed fascinating what a smart guy with a laptop can do at home… I’m an engineer and passionate about gaming, I couldn’t even think of how to accomplish such thing. Congrats to the author! 👏🏻

@PaulOsbornesChannel @PaulOsbornesChannel  23/10/01 17:46  polubiono  1372

The way you taught it to drift, then taught it to use drifting to go faster was brilliant

@Bassalicious @Bassalicious  23/10/01 13:04  polubiono  1116

This is nuts. The sheer amount of work involved boggles the mind. Such a well paced and chill presentation too, love it!

@RacetasClub @RacetasClub  23/09/30 19:47  polubiono  894

What a magnificent video and what an incredible journey. This got me excited all over again. You sir took quality to a whole new level, you & the AI should both be very proud :)

@benslater4997 @benslater4997  23/10/06 22:59  polubiono  712

16:19 I love how the Ai found a way to abuse the crap out of the reward system 😂

@BBweed420 @BBweed420  23/10/09 03:46  polubiono  682

I absolutely love the part where it becomes the drift king for optimal rewards. Just styling by doing micro drifts constantly.

@kootenpv @kootenpv  23/11/11 10:29  polubiono  593

The main problem with the final test is that this part of the map was still contained in the training data, and for that it means it likely doesn't generalize and instead was over fit at least slightly

@johnbrooks6243 @johnbrooks6243  23/10/02 16:40  polubiono  589

Watching your own creation grown and outperform you has such a paternal feeling its amazing.

@brigbrizz @brigbrizz  23/10/06 14:24  polubiono  570

This was so much fun to watch! Thank you for putting it together, and posting it for us to enjoy!

@DjupDjupTheLightningSloth @DjupDjupTheLightningSloth  23/10/02 20:09  polubiono  553

I hope Wirtual does a followup. Would also be fun if the devs release an AI medal on each map

@holyyoghurtman1952 @holyyoghurtman1952  23/10/08 09:31  polubiono  549

Shoutout to the one iteration of the AI that managed to fuck up so spectacularly it went over the railings at 2:33

@Hacks-rx2jc @Hacks-rx2jc  23/10/15 22:33  polubiono  511

This is the spirit of coding, and CS in general. Trying new things that you aren't certain about. Learning by doing. Thank you for putting in over 3 years to make this masterpiece. BTW can we -steal- *borrow* the training data pls?