Loading video...

Video Failed to Load

Go Home

This is how Microduck learns to walk. Reinforcement Learning, explained by ducks. 🦆 (impeccable) music arrangement by Antoine Pirrone

RemiFabreRobot's profile picture

Remi Fabre

3,825 subscribers

62,751 views • 3 days ago •via X (Twitter)

Science & TechnologyEducationMusic
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Sexy soft steps.Adam learned to walk like a human,trained by reinforcement learning.
1:20

Sexy soft steps.Adam learned to walk like a human,trained by reinforcement learning.

CyberRobo

19,732 views • 1 year ago

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

837,871 views • 2 years ago

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!
53:45

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,772 views • 2 months ago

The future of robotics isn’t being built in factories, it’s being trained in simulation MasterBOT’s proprietary AI model is learning in real-time, powered by reinforcement and continuous feedback loops This is how machines learn to think $BOT
4:34

The future of robotics isn’t being built in factories, it’s being trained in simulation MasterBOT’s proprietary AI model is learning in real-time, powered by reinforcement and continuous feedback loops This is how machines learn to think $BOT

MasterBOT

51,189 views • 10 months ago

Peter of Psquare is trying to avoid paying his producers by using AI to make his music… in this video I explained how he did it. Anyone can do this.
2:36

Peter of Psquare is trying to avoid paying his producers by using AI to make his music… in this video I explained how he did it. Anyone can do this.

DAYGENIUS☀️

48,840 views • 1 month ago

How many ducks are in this image? 😂 London City Lionesses did their best to find out 🦆
1:20

How many ducks are in this image? 😂 London City Lionesses did their best to find out 🦆

Match of the Day

80,014 views • 7 months ago

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.
1:01

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.

Praveen Kumar Verma

133,238 views • 8 days ago

Rescue chicken learns to walk by wearing shoes — and now he has over 30 pairs ❤️
3:02

Rescue chicken learns to walk by wearing shoes — and now he has over 30 pairs ❤️

The Dodo

673,346 views • 3 years ago

How to Identify Anti National Politicians... Explained by This sikh brother... And the pattern is same among these politicians!
0:52

How to Identify Anti National Politicians... Explained by This sikh brother... And the pattern is same among these politicians!

Vineeta Singh 🇮🇳

19,687 views • 5 months ago

the full meaning of yuna’s ice cream music video explained by this tiktok
0:31

the full meaning of yuna’s ice cream music video explained by this tiktok

🪽

69,866 views • 5 months ago

How to Lose Weight Explained by Gary Brecka
2:02

How to Lose Weight Explained by Gary Brecka

Fitness Hub2.0

250,690 views • 4 months ago

How To Increase Testosterone Naturally Explained By Monkey
1:31

How To Increase Testosterone Naturally Explained By Monkey

Testosterone Doctor

145,619 views • 2 months ago

Today on my electronic music journey: learning how to make hi-tech (Area Zero battle by Toby fox & Go ichinose)
0:36

Today on my electronic music journey: learning how to make hi-tech (Area Zero battle by Toby fox & Go ichinose)

onion_mu

14,444 views • 6 months ago

When people walk side by side with open hearts, nations, languages, and borders slowly fade into the background. What remains is humanity shared suffering, shared hope, and a shared responsibility to choose peace. This is how the world learns again. #WalkForPeace 🕊️🪷 ☸️
0:30

When people walk side by side with open hearts, nations, languages, and borders slowly fade into the background. What remains is humanity shared suffering, shared hope, and a shared responsibility to choose peace. This is how the world learns again. #WalkForPeace 🕊️🪷 ☸️

🦋Beyond_Horizon

15,514 views • 7 months ago

How to approach trading explained by a psychologist without knowing she is talking about trading.
2:34

How to approach trading explained by a psychologist without knowing she is talking about trading.

BankofVol Grift¹⁰⁰⁰🤖🤖¹⁰⁰⁰⁰⁰⁰

64,463 views • 1 year ago

Damn this is good. THAT’S HOW YOU START! Lakas kutob ko na this is how they’ll do their music sa Coachella. Recorded live band arrangement
3:15

Damn this is good. THAT’S HOW YOU START! Lakas kutob ko na this is how they’ll do their music sa Coachella. Recorded live band arrangement

Ash

137,389 views • 6 months ago

A song featuring 3 women, sung by one man. Wonder how this situation was even narrated to Ilaiyaraaja and how he chose to sing this one. This song is an orchestral piece by Ilayaraja. The violin fills and the overall arrangement are beautifully stitched together.
4:35

A song featuring 3 women, sung by one man. Wonder how this situation was even narrated to Ilaiyaraaja and how he chose to sing this one. This song is an orchestral piece by Ilayaraja. The violin fills and the overall arrangement are beautifully stitched together.

Sriram

19,702 views • 9 months ago

How to bass sound design!!! This song is out now on Monstercat !!!! background music: Dolphin Valley by wwhhooami
1:52

How to bass sound design!!! This song is out now on Monstercat !!!! background music: Dolphin Valley by wwhhooami

Glitch Cat

28,800 views • 1 month ago

Daniel Kokotajlo says companies are making AI more agentic by scaling RL (reinforcement learning) and connecting agents to various tools. by early 2027, these agents will be fully autonomous, superhuman coders able to replace human programmers.
1:05

Daniel Kokotajlo says companies are making AI more agentic by scaling RL (reinforcement learning) and connecting agents to various tools. by early 2027, these agents will be fully autonomous, superhuman coders able to replace human programmers.

Haider.

11,572 views • 1 year ago