Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Baby steps towards physically based animation with reinforcement learning...

voxagonlabs's profile picture

Dennis Gustafsson

84,573 subscribers

32,132 görüntüleme • 1 yıl önce •via X (Twitter)

OyunBilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Kiaran Ritchie profil fotoğrafı
Kiaran Ritchie1 yıl önce

I've gone down this path before. Ended up writing reward functions to reward foot height over time within a periodic gait cycle. Use this just to get them stepping, then use a curriculum to turn this reward off and let the policy find a more natural gait pattern by penalizing energy. Had to penalize foot sliding too because they get lazy haha

Dennis Gustafsson profil fotoğrafı
Dennis Gustafsson1 yıl önce

Interesting, what happened if you didn't do all that? Just weird motion, or didn't learn at all?

Kids Fundamentals profil fotoğrafı
Kids Fundamentals1 yıl önce

Invest in your child's future success today with our Name Tracing Practice Board. Kid approved!

Nikita Lisitsa profil fotoğrafı
Nikita Lisitsa1 yıl önce

Super fun! I tried this in 2D once, though I used evolutionary methods - never managed to get RL working :/

Dennis Gustafsson profil fotoğrafı
Dennis Gustafsson1 yıl önce

Very cool! Can you explain a bit what you mean by evolutionary model? Randomizing weights in batches and move towards the winner? I'm using standard RL techniques (this one uses PPO)

Simon's Limit Exceeded 🕳️ profil fotoğrafı
Simon's Limit Exceeded 🕳️1 yıl önce

I failed trying to make objects walk mechanically. Can you hear them screaming "kill me"?

bot_0 profil fotoğrafı
bot_01 yıl önce

Duuude! Finally someone doing (showing) game stuff related to AI models (that aren't just text/llm based). Massive potential here imo. The physics modelling could be huge too, but I guess the Teardown engine's physics is so optimised anyway it may not be needed! Exciting times!

Fb01 profil fotoğrafı
Fb011 yıl önce

Karl sims lives( I know he’s thankfully very much alive ;)

Stocko 👊🤖 profil fotoğrafı
Stocko 👊🤖1 yıl önce

nice!

Topotoy Labs profil fotoğrafı
Topotoy Labs1 yıl önce

Delightfully creepy!

Benzer Videolar

Baby Quartz learning some dancing steps yesterday.
0:27

Baby Quartz learning some dancing steps yesterday.

Robert W Malone, MD

23,364 görüntüleme • 10 ay önce

Reinforcement learning
0:39

Reinforcement learning

Massimo

3,407,847 görüntüleme • 2 yıl önce

RL-100 Performant Robotic Manipulation with Real-World Reinforcement Learning
1:37

RL-100 Performant Robotic Manipulation with Real-World Reinforcement Learning

AK

15,364 görüntüleme • 8 ay önce

Redwood AI | Mobility Reinforcement Learning
1:01

Redwood AI | Mobility Reinforcement Learning

1X

1,318,162 görüntüleme • 1 yıl önce

Training AI to Play Pokemon with Reinforcement Learning by Peter Whidden github: youtube:
1:19

Training AI to Play Pokemon with Reinforcement Learning by Peter Whidden github: youtube:

AK

837,726 görüntüleme • 2 yıl önce

An interesting example of reinforcement learning.
0:39

An interesting example of reinforcement learning.

Historic Vids

1,563,912 görüntüleme • 3 yıl önce

An Interesting example of Reinforcement learning!! 🐓
0:39

An Interesting example of Reinforcement learning!! 🐓

OpenMoon

7,058,853 görüntüleme • 2 yıl önce

how to learn something from the first principles (with a live demo on reinforcement learning)
39:05

how to learn something from the first principles (with a live demo on reinforcement learning)

Ajeet ( opensox.ai )

229,818 görüntüleme • 1 ay önce

Getting Cyn ready for reinforcement learning >:3
0:47

Getting Cyn ready for reinforcement learning >:3

DT

14,256 görüntüleme • 8 ay önce

i trained a reinforcement learning agent to play diablo 1 in a few hours with pufferlib
0:50

i trained a reinforcement learning agent to play diablo 1 in a few hours with pufferlib

Dan Advantage

41,954 görüntüleme • 7 ay önce

robot named CyberRunner, developed by researchers at ETH Zurich, which uses Al and model-based reinforcement learning to master the classic Labyrinth board game in just six hours
0:20

robot named CyberRunner, developed by researchers at ETH Zurich, which uses Al and model-based reinforcement learning to master the classic Labyrinth board game in just six hours

Science girl

120,161 görüntüleme • 10 ay önce

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.
1:10

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

RAI Institute

76,576 görüntüleme • 1 yıl önce

Years of reinforcement learning in one clip: Atlas pulls off a cartwheel-to-backflip combo with perfect balance.
0:20

Years of reinforcement learning in one clip: Atlas pulls off a cartwheel-to-backflip combo with perfect balance.

Big Brain AI

91,490 görüntüleme • 1 ay önce

NEW: Disney reveals “ReActor,” a new method for Walt Disney Imagineering’s robotic character pipeline. • Combines reinforcement learning with physics-based simulations to transfer human motion to characters • Could be the next milestone for more lifelike robotic characters
5:40

NEW: Disney reveals “ReActor,” a new method for Walt Disney Imagineering’s robotic character pipeline. • Combines reinforcement learning with physics-based simulations to transfer human motion to characters • Could be the next milestone for more lifelike robotic characters

Drew Smith

66,818 görüntüleme • 1 ay önce

One small step for man, one giant leap for baby kind. Baby Steps, the physics-based puzzler, has landed on PS5:
1:21

One small step for man, one giant leap for baby kind. Baby Steps, the physics-based puzzler, has landed on PS5:

PlayStation UK

16,161 görüntüleme • 9 ay önce

Learning a new skill is can be so overwhelming. But try taking baby steps instead. Ps: if you have any YouTube recommendations you feel would help me in my learning process with Framer, share them with me. #uiuxdesign #WebDevelopment
1:47

Learning a new skill is can be so overwhelming. But try taking baby steps instead. Ps: if you have any YouTube recommendations you feel would help me in my learning process with Framer, share them with me. #uiuxdesign #WebDevelopment

Emilia

32,261 görüntüleme • 1 yıl önce

DeepMind training bipedal robots to play soccer using deep reinforcement learning.
0:27

DeepMind training bipedal robots to play soccer using deep reinforcement learning.

MachinePix

16,986,259 görüntüleme • 2 yıl önce

Figure 02 robots are now walking with a smoother gait and increased speed, thanks to sim-to-real reinforcement learning.
0:51

Figure 02 robots are now walking with a smoother gait and increased speed, thanks to sim-to-real reinforcement learning.

The Humanoid Hub

146,868 görüntüleme • 1 yıl önce

Talk2Move Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
1:43

Talk2Move Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

AK

10,719 görüntüleme • 5 ay önce

FP4 Explore, BF16 Train Diffusion Reinforcement Learning via Efficient Rollout Scaling paper:
0:35

FP4 Explore, BF16 Train Diffusion Reinforcement Learning via Efficient Rollout Scaling paper:

AK

12,778 görüntüleme • 2 ay önce