Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I'm launching dingbotics: speeding up RL for robotics go to dingbotics dot com to check out the latest model I've trained. this will work on your phone's web browser built with mujoco, nvidia warp, pufferlib, raylib & Rich the Kid

yacineMTB's profile picture

kache

295,292 subscribers

38,676 görüntüleme • 18 gün önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

success!! trained with pufferlib with my 4090 this was trained against a captured cudagraph from mujoco warp. the training loop runs at 250k SPS. this is 2 hours to train Still not as good as the baseline. But its mine! Same obs & action set up as mujoco playground
0:26

success!! trained with pufferlib with my 4090 this was trained against a captured cudagraph from mujoco warp. the training loop runs at 250k SPS. this is 2 hours to train Still not as good as the baseline. But its mine! Same obs & action set up as mujoco playground

kache

21,579 görüntüleme • 18 gün önce

For this hackathon I taught a robot to beat you in Jenga. It sims every possible move, picks the block that's the best move, then an RL policy pushes it out. Built in MuJoCo & Three.js, running on a real AgileX Robotics arm.
0:30

For this hackathon I taught a robot to beat you in Jenga. It sims every possible move, picks the block that's the best move, then an RL policy pushes it out. Built in MuJoCo & Three.js, running on a real AgileX Robotics arm.

jonathanhawkins

39,496 görüntüleme • 1 ay önce

I'm super excited to announce mjlab today! mjlab = Isaac Lab's APIs + best-in-class MuJoCo physics + massively parallel GPU acceleration Built directly on MuJoCo Warp with the abstractions you love.
0:37

I'm super excited to announce mjlab today! mjlab = Isaac Lab's APIs + best-in-class MuJoCo physics + massively parallel GPU acceleration Built directly on MuJoCo Warp with the abstractions you love.

Kevin Zakka

91,840 görüntüleme • 9 ay önce

Really excited to release mjviser, a web-based MuJoCo viewer, powered by Viser. It has almost all the features of the native MuJoCo viewer, but runs in your browser. Load and simulate any MuJoCo model with a single uv command 👇 uvx mjviser
0:57

Really excited to release mjviser, a web-based MuJoCo viewer, powered by Viser. It has almost all the features of the native MuJoCo viewer, but runs in your browser. Load and simulate any MuJoCo model with a single uv command 👇 uvx mjviser

Kevin Zakka

22,514 görüntüleme • 3 ay önce

We're also launching the Gemini Robotics software development kit (SDK) to help developers fine-tune the model for their own applications, including by testing it in the MuJoCo physics simulator. 🌐
0:23

We're also launching the Gemini Robotics software development kit (SDK) to help developers fine-tune the model for their own applications, including by testing it in the MuJoCo physics simulator. 🌐

Google DeepMind

34,238 görüntüleme • 1 yıl önce

hi all, excited to join! i'm building an expressive mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target design
0:29

hi all, excited to join! i'm building an expressive mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target design

Matthieu LC

45,506 görüntüleme • 1 yıl önce

The dot com bubble moment for crypto has popped with altcoins Most go to $0 & some will change the world
2:11

The dot com bubble moment for crypto has popped with altcoins Most go to $0 & some will change the world

Finance Freeman 🇺🇸

168,135 görüntüleme • 24 gün önce

We just open-sourced luwu_mjlab: an RL training environment for Luwu Dynamics quadruped robots. Built on mjlab + MuJoCo Warp, it lets us train locomotion and get-up policies in simulation, then validate them on real robots. GitHub:
0:32

We just open-sourced luwu_mjlab: an RL training environment for Luwu Dynamics quadruped robots. Built on mjlab + MuJoCo Warp, it lets us train locomotion and get-up policies in simulation, then validate them on real robots. GitHub:

XGO Robot

11,563 görüntüleme • 16 gün önce

I'm really warming up to KC Concepcion. Check out this interview feature about him and struggling while growing up with a stutter. Phenomenal kid. Zero WR Diva. He's the anti-OBJ. And go check out his open letter to NFL GMs on the Players Tribune if you haven't yet.
1:59

I'm really warming up to KC Concepcion. Check out this interview feature about him and struggling while growing up with a stutter. Phenomenal kid. Zero WR Diva. He's the anti-OBJ. And go check out his open letter to NFL GMs on the Players Tribune if you haven't yet.

Roberto Shenanigans

34,603 görüntüleme • 2 ay önce

🤔Want a principled way to RL your diffusion model? Check Data-regularized Reinforcement Learning (DDRL)! Post-train NVIDIA #Cosmos World Foundation models with a million GPU hours! 🤯 Novel formulation ➡️ Theoretically integrates SFT into RL ➡️ Robust to Reward Hacking 🛑 Details: #DDRL #Diffusion #RL #NVIDIA #Cosmos
0:20

🤔Want a principled way to RL your diffusion model? Check Data-regularized Reinforcement Learning (DDRL)! Post-train NVIDIA #Cosmos World Foundation models with a million GPU hours! 🤯 Novel formulation ➡️ Theoretically integrates SFT into RL ➡️ Robust to Reward Hacking 🛑 Details: #DDRL #Diffusion #RL #NVIDIA #Cosmos

Haotian Ye

77,612 görüntüleme • 6 ay önce

With the latest version of qgis2threejs in QGIS you can set your 3D scenes to autoplay in the browser, following any path you like (as you can see I need to work on this!) - here's the live web page example shown in the video #QGIS
0:25

With the latest version of qgis2threejs in QGIS you can set your 3D scenes to autoplay in the browser, following any path you like (as you can see I need to work on this!) - here's the live web page example shown in the video #QGIS

Alasdair Rae

61,462 görüntüleme • 3 yıl önce

Summer storms combined with high volume are leading to high levels of air travel disruption this week. DOT will continue our work to support passengers & promote resiliency in the airline system. If you’re flying, be sure to check out to know your rights.
1:20

Summer storms combined with high volume are leading to high levels of air travel disruption this week. DOT will continue our work to support passengers & promote resiliency in the airline system. If you’re flying, be sure to check out to know your rights.

Secretary Pete Buttigieg

627,610 görüntüleme • 3 yıl önce

"I'm not waiting until I'm done to go head first into this." Check out our latest conversation featuring Saints running back & NASCAR's Growth and Engagement Advisor Alvin Kamara on the Sports Spectrum podcast with Matt Forte.
0:39

"I'm not waiting until I'm done to go head first into this." Check out our latest conversation featuring Saints running back & NASCAR's Growth and Engagement Advisor Alvin Kamara on the Sports Spectrum podcast with Matt Forte.

Sports Spectrum

17,266 görüntüleme • 11 ay önce

Dex is ready for the factory floor. 🏭 Learn how Richtech Robotics built this mobile humanoid robot, powered by NVIDIA Jetson AGX Thor and trained in Isaac Sim, to handle light to medium industrial tasks. Read the blog ➡️
0:36

Dex is ready for the factory floor. 🏭 Learn how Richtech Robotics built this mobile humanoid robot, powered by NVIDIA Jetson AGX Thor and trained in Isaac Sim, to handle light to medium industrial tasks. Read the blog ➡️

NVIDIA Robotics

25,381 görüntüleme • 6 ay önce

Jensen just announced Newton, an open-source physics engine for robotics simulation developed by NVIDIA, Google DeepMind, and Disney Research. ⦿ Built on NVIDIA Warp, it offers GPU-accelerated performance and compatibility with frameworks like MuJoCo and Isaac Lab. ⦿ Features differentiable physics, extensibility for multiphysics simulations, and integration with OpenUSD for flexible data modeling. ⦿ Newton addresses the sim-to-real gap by creating realistic virtual environments for robot training and testing. ⦿ Disney Research is using Newton to power next-gen entertainment robots, including Star Wars-inspired BDX droids.
3:32

Jensen just announced Newton, an open-source physics engine for robotics simulation developed by NVIDIA, Google DeepMind, and Disney Research. ⦿ Built on NVIDIA Warp, it offers GPU-accelerated performance and compatibility with frameworks like MuJoCo and Isaac Lab. ⦿ Features differentiable physics, extensibility for multiphysics simulations, and integration with OpenUSD for flexible data modeling. ⦿ Newton addresses the sim-to-real gap by creating realistic virtual environments for robot training and testing. ⦿ Disney Research is using Newton to power next-gen entertainment robots, including Star Wars-inspired BDX droids.

The Humanoid Hub

127,482 görüntüleme • 1 yıl önce

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more
0:41

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more

Prime Intellect

1,137,660 görüntüleme • 7 ay önce

Ideogram 4.0 is the image model built for design, now where the rest of your work already lives. Check out Ideogram in FLORA.
0:20

Ideogram 4.0 is the image model built for design, now where the rest of your work already lives. Check out Ideogram in FLORA.

FLORA ©

10,873 görüntüleme • 20 gün önce

🤯🤯🤯 An in-browser REPL for Laravel ? With autocomplete? And access to local variables? For every frame of the stack trace? Yup...this blows my mind and I'm so excited about this! Go check this out 🧪
4:53

🤯🤯🤯 An in-browser REPL for Laravel ? With autocomplete? And access to local variables? For every frame of the stack trace? Yup...this blows my mind and I'm so excited about this! Go check this out 🧪

Marcel Pociot 🧪

31,406 görüntüleme • 6 ay önce

‘A Pale White Dot’ is OUT NOW everywhere, along with the music video for “Heaven on High.” Listen to the album & check out the video at Thank you for all the love on this one. 🖤 Vinyl & merch are also available at
0:37

‘A Pale White Dot’ is OUT NOW everywhere, along with the music video for “Heaven on High.” Listen to the album & check out the video at Thank you for all the love on this one. 🖤 Vinyl & merch are also available at

Periphery

18,605 görüntüleme • 1 ay önce

Rich shuts down all this made-up SGA hate🗣️ Check out the full rant in latest episode of RT out now on YouTube & Wondery🚐 📺 🎧
2:05

Rich shuts down all this made-up SGA hate🗣️ Check out the full rant in latest episode of RT out now on YouTube & Wondery🚐 📺 🎧

Road Trippin’ Show

81,711 görüntüleme • 1 yıl önce