Loading video...

Video Failed to Load

Go Home

Reinforcement learning doesn't work ... until it does!

TheHumanoidAI's profile picture

Humanoid

6,255 subscribers

11,571 views • 12 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

2 Comments

Nicolas Brusco's profile picture
Nicolas Brusco12 days ago

The hardest part about RL is that “broken” is indistinguishable from “needs to train for longer” Ask me how much electricity I’ve wasted.

OpsyRobot's profile picture
OpsyRobot11 days ago

Reinforcement learning is the best practical way to teach robots

Related Videos

Reinforcement learning
0:39

Reinforcement learning

Massimo

3,407,939 views • 2 years ago

"Be kind until kindness doesn't work" does not appear in the Bible. David French
5:26

"Be kind until kindness doesn't work" does not appear in the Bible. David French

Good Faith

113,161 views • 3 years ago

Redwood AI | Mobility Reinforcement Learning
1:01

Redwood AI | Mobility Reinforcement Learning

1X

1,326,832 views • 1 year ago

“Submit to Rome” doesn’t work… until it does.
1:47

“Submit to Rome” doesn’t work… until it does.

𝚕𝚒𝚝𝚝𝚕𝚎 𝚘𝚗𝚎 ♱🇻🇦

15,185 views • 7 months ago

An interesting example of reinforcement learning.
0:39

An interesting example of reinforcement learning.

Historic Vids

1,564,042 views • 3 years ago

This Namor ability doesn't work how you think it does 🐟
0:41

This Namor ability doesn't work how you think it does 🐟

FlyQuest Rivals

162,362 views • 1 year ago

Reinforcement learning experiments continues. Still a bit janky, but it is clearly learning something. This is about an hour into training.
0:49

Reinforcement learning experiments continues. Still a bit janky, but it is clearly learning something. This is about an hour into training.

Dennis Gustafsson

22,642 views • 1 year ago

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

An Interesting example of Reinforcement learning!! 🐓

OpenMoon

7,059,237 views • 2 years ago

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

Getting Cyn ready for reinforcement learning >:3

DT

14,557 views • 1 year ago

For researchers, scientists, and academics tackling hard problems: Gemini 2.5 Deep Think is here. 🤯 It doesn't just answer, it brainstorms using parallel thinking and reinforcement learning techniques. We put it into the hands of mathematicians who explored what it can do ↓
1:13

For researchers, scientists, and academics tackling hard problems: Gemini 2.5 Deep Think is here. 🤯 It doesn't just answer, it brainstorms using parallel thinking and reinforcement learning techniques. We put it into the hands of mathematicians who explored what it can do ↓

Google DeepMind

853,090 views • 1 year ago

Baby steps towards physically based animation with reinforcement learning...
0:42

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

Dennis Gustafsson

33,418 views • 1 year ago

DBFZ v1.50 Daima Goku, sparking combo #1 from 2H midscreen. *sees Cell* "Does it work on-" No it doesn't work at all 🗿
0:20

DBFZ v1.50 Daima Goku, sparking combo #1 from 2H midscreen. *sees Cell* "Does it work on-" No it doesn't work at all 🗿

Xiao (蕭)

50,341 views • 6 months ago

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 views • 1 year ago

Rebar work Reinforcement 😱
1:00

Rebar work Reinforcement 😱

Civil Engineering Discoveries

246,205 views • 2 years ago

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

16,995,716 views • 3 years ago

Today's robots are too unreliable and slow for real industrial work. Reinforcement learning changes that. Meet KinetIQ Ascend: our robots practice real production tasks and improve predictably towards industrial reliability standards. How it works 🧵
1:40

Today's robots are too unreliable and slow for real industrial work. Reinforcement learning changes that. Meet KinetIQ Ascend: our robots practice real production tasks and improve predictably towards industrial reliability standards. How it works 🧵

hr0nix

11,275 views • 4 months ago

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

12,817 views • 6 months ago

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

10,801 views • 10 months ago