kache's banner
kache's profile picture

kache

@yacineMTB329,341 subscribers

reinforcement learning, robots. prev eng @ x, stripe. 6'3 (height) tensorpunk subscribe to read my blog!

Shorts

I wrote my own CAD software whose intended user is an AI. I asked GPT 5.6 sol to make me a case for my camera. It only interrupted me once, which was to log in to a website to download a model of my camera as reference. Not perfect but.. pretty crazy :)

I wrote my own CAD software whose intended user is an AI. I asked GPT 5.6 sol to make me a case for my camera. It only interrupted me once, which was to log in to a website to download a model of my camera as reference. Not perfect but.. pretty crazy :)

92,444 Aufrufe

Dennis Gustafsson me and gpt 5.5 found a bug that didn't make it deterministic and fixed it

Dennis Gustafsson me and gpt 5.5 found a bug that didn't make it deterministic and fixed it

152,633 Aufrufe

This is running in my web browser on my laptop. It's deterministic and running using webgpu Tonight; I have a /goal going where it is going to set up one of my 4090s as the authority server, and then test all the rollback code. Goal is 50k boxes simmed per user, up to 512 users. Massively multiplayer massively rigid body physics online games inside your web browser. Why the hell not, we've got the tokens to spare!

This is running in my web browser on my laptop. It's deterministic and running using webgpu Tonight; I have a /goal going where it is going to set up one of my 4090s as the authority server, and then test all the rollback code. Goal is 50k boxes simmed per user, up to 512 users. Massively multiplayer massively rigid body physics online games inside your web browser. Why the hell not, we've got the tokens to spare!

36,148 Aufrufe

I just trained cartpole in mujoco at 18 million steps per second. This policy learned in **less than 3 seconds** rollout policy batch size was 8192 agents

I just trained cartpole in mujoco at 18 million steps per second. This policy learned in **less than 3 seconds** rollout policy batch size was 8192 agents

68,441 Aufrufe

"how many experiments have you run" yes

"how many experiments have you run" yes

45,350 Aufrufe

what if you simulated every single particle of your robot would it be parallelizable then?

what if you simulated every single particle of your robot would it be parallelizable then?

31,586 Aufrufe

researcher friend of mine shared this with me; comfree-sim. which is basically existence proof of my hunch: mujoco has terrible performance, and there are probably huge huge gains you can make in training, especially considering domain randomization

researcher friend of mine shared this with me; comfree-sim. which is basically existence proof of my hunch: mujoco has terrible performance, and there are probably huge huge gains you can make in training, especially considering domain randomization

35,284 Aufrufe

I've gotten a mujoco sim RL training loop for a unitree robot at 200k SPS. I'm looking into the physics for friction, contact dynamics. My goal: can I reproduce & beat the mujoco playground RL baselines This is running in my web browser with raylib. Its the baseline

I've gotten a mujoco sim RL training loop for a unitree robot at 200k SPS. I'm looking into the physics for friction, contact dynamics. My goal: can I reproduce & beat the mujoco playground RL baselines This is running in my web browser with raylib. Its the baseline

29,728 Aufrufe

today; the goal is to reduce the time of training for this by 10x. This took 27.8 minutes to train at 200m steps 120k steps per second. reproduction from mujoco playground using mjwarp

today; the goal is to reduce the time of training for this by 10x. This took 27.8 minutes to train at 200m steps 120k steps per second. reproduction from mujoco playground using mjwarp

27,376 Aufrufe

6 pendulums probably in 5 hours

6 pendulums probably in 5 hours

26,064 Aufrufe

I'm building the Canadian DJI with a debit card

I'm building the Canadian DJI with a debit card

33,993 Aufrufe

my first fluid sim

my first fluid sim

35,400 Aufrufe

Fixed a numerics bug on the training loop, and got the training down from 52 minutes to 45 minutes Only 15 minutes away from beating the deepmind mujoco playground baseline!

Fixed a numerics bug on the training loop, and got the training down from 52 minutes to 45 minutes Only 15 minutes away from beating the deepmind mujoco playground baseline!

19,248 Aufrufe

configuring nvim for 5 hours today was worth it look at this cute lil guy

configuring nvim for 5 hours today was worth it look at this cute lil guy

136,084 Aufrufe

i want to show you guys how fast programming is now i'm kind of resurrecting dingboard zig to see how fast i can make progress on it, using it as a test bed to see AI progress it took me 5 minutes to add a GPU accelerated (!) mirror button now, watch how fast this next thing is

i want to show you guys how fast programming is now i'm kind of resurrecting dingboard zig to see how fast i can make progress on it, using it as a test bed to see AI progress it took me 5 minutes to add a GPU accelerated (!) mirror button now, watch how fast this next thing is

138,298 Aufrufe

live on my website again. i'm designing the internet condom. Trying to understand the difference of search and recommendations, figuring out what an MVP can look like, trying to design something that can actually beat all social media networks, something that would destroy them

live on my website again. i'm designing the internet condom. Trying to understand the difference of search and recommendations, figuring out what an MVP can look like, trying to design something that can actually beat all social media networks, something that would destroy them

16,064 Aufrufe

right now my reinforcement learning model is basically doing this and i came up with a solution for it all by myself (by stealing it from pufferlib) that not only solves it, but also helps keep training stable and fast

right now my reinforcement learning model is basically doing this and i came up with a solution for it all by myself (by stealing it from pufferlib) that not only solves it, but also helps keep training stable and fast

60,094 Aufrufe

just added skins. do you guys see this?

just added skins. do you guys see this?

85,568 Aufrufe

well it's getting one of them up..

well it's getting one of them up..

11,734 Aufrufe

Videos

yacineMTB's profile picture

programming in 2024

kache

1,652,675 Aufrufe • vor 1 Jahr

yacineMTB's profile picture

i love this stuff so much

kache

55,933 Aufrufe • vor 1 Monat

yacineMTB's profile picture

my second fluid sim

kache

41,239 Aufrufe • vor 2 Monaten