Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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

Dennis Gustafsson

84,462 subscribers

22,642 Aufrufe • vor 11 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Frontier models that use reasoning to "think" during inference are generating 5X more AI tokens per year. ✨ "Inference is now a thinking process. And in order to teach AI how to think, reinforcement learning and very significant computation was introduced into post-training," said NVIDIA CEO Jensen Huang in a recent keynote at #CES2026. Reinforcement learning is increasing computation demands across all AI scaling laws: pre-training, post-training, and test-time scaling. Learn more about reinforcement learning and AI scaling ➡️

Frontier models that use reasoning to "think" during inference are generating 5X more AI tokens per year. ✨ "Inference is now a thinking process. And in order to teach AI how to think, reinforcement learning and very significant computation was introduced into post-training," said NVIDIA CEO Jensen Huang in a recent keynote at #CES2026. Reinforcement learning is increasing computation demands across all AI scaling laws: pre-training, post-training, and test-time scaling. Learn more about reinforcement learning and AI scaling ➡️

NVIDIA AI Infrastructure

13,329 Aufrufe • vor 6 Monaten

2026 is about learning something new

2026 is about learning something new

alec

17,678 Aufrufe • vor 6 Monaten

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.

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

76,647 Aufrufe • vor 1 Jahr

Kai Cenat LOST IT after IShowSpeed admitted he is still learning how to play Minecraft on hour 93 of their Hardcore Minecraft Marathon 😭 Speed: “I’m learning about the game” Kai: “FOR HOW LONG”

Kai Cenat LOST IT after IShowSpeed admitted he is still learning how to play Minecraft on hour 93 of their Hardcore Minecraft Marathon 😭 Speed: “I’m learning about the game” Kai: “FOR HOW LONG”

yoxic

1,276,161 Aufrufe • vor 1 Tag

David Silver says human data is AI's fossil fuel. "We mine it and burn it in our LLMs." It gave us a head start -- but it will run out. The sustainable path is reinforcement learning: systems that learn from experience, generate more, and keep learning.

David Silver says human data is AI's fossil fuel. "We mine it and burn it in our LLMs." It gave us a head start -- but it will run out. The sustainable path is reinforcement learning: systems that learn from experience, generate more, and keep learning.

vitrupo

20,194 Aufrufe • vor 1 Jahr

You may not like it, but this is how the next generation’s Warren Buffett is learning about finance

You may not like it, but this is how the next generation’s Warren Buffett is learning about finance

Trust Fund Terry

66,891 Aufrufe • vor 1 Jahr

Reinforcement Learning is the future tense of intelligence. Echo is how it scales. Echo is Gradient’s distributed RL framework, running on everyday consumer devices. From its early experiments, Echo powered a 30B Sokoban model that outperformed DeepSeek-R1 and GPT-OSS-120B.

Reinforcement Learning is the future tense of intelligence. Echo is how it scales. Echo is Gradient’s distributed RL framework, running on everyday consumer devices. From its early experiments, Echo powered a 30B Sokoban model that outperformed DeepSeek-R1 and GPT-OSS-120B.

Gradient

279,191 Aufrufe • vor 11 Monaten

I already said this before but I'm gonna say it again.. Jongdae's English is really great?? His prononciation is on point too 😭 This dude is clearly learning English

I already said this before but I'm gonna say it again.. Jongdae's English is really great?? His prononciation is on point too 😭 This dude is clearly learning English

卌 𝓵𝓞𝓾 🎸𝐀𝐑𝐂𝐀𝐃𝐈𝐀 🤘

34,122 Aufrufe • vor 10 Monaten

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

naklecha

46,795 Aufrufe • vor 1 Jahr

Little Language Lessons is a collection of bite-sized learning experiments built with the Gemini API - try it today →

Little Language Lessons is a collection of bite-sized learning experiments built with the Gemini API - try it today →

Google Labs

82,236 Aufrufe • vor 1 Jahr

The dog is still learning this trick: 👀

The dog is still learning this trick: 👀

AlphaFox

2,914,990 Aufrufe • vor 1 Jahr

This is why learning about other cultures is fun

This is why learning about other cultures is fun

𝕯𝖆𝛎𝖎𝐝🧘🏾‍♂️

17,141 Aufrufe • vor 5 Monaten

This isn’t an attack, just an observation. Content creation isn’t something you jump into casually, It takes learning, skill, and intention. Web3 has many paths, video content is only one of them. If this doesn’t apply to you, then it’s not about you.

This isn’t an attack, just an observation. Content creation isn’t something you jump into casually, It takes learning, skill, and intention. Web3 has many paths, video content is only one of them. If this doesn’t apply to you, then it’s not about you.

Whisper 🌺

122,599 Aufrufe • vor 7 Monaten

Model shaping is still a craft of a few. That's what AI agents are for: learning it and doing it for everyone else. As a part of FrontierSWE benchmark we built a 20-hour post-training task on Tinker and found the real bottleneck is research intuition.

Model shaping is still a craft of a few. That's what AI agents are for: learning it and doing it for everyone else. As a part of FrontierSWE benchmark we built a 20-hour post-training task on Tinker and found the real bottleneck is research intuition.

Thoughtful

226,335 Aufrufe • vor 3 Monaten

KL divergence is a fundamental concept used in machine learning, from optimization a neural net to RL training of LLMs. but here is what it actually means:

KL divergence is a fundamental concept used in machine learning, from optimization a neural net to RL training of LLMs. but here is what it actually means:

ℏεsam

20,381 Aufrufe • vor 6 Monaten

Watch Gemini 2.5 Pro implement a landmark Google DeepMind research paper. 🕹️ It codes the reinforcement learning algorithm, visualizes the training live and even debugs errors. ↓

Watch Gemini 2.5 Pro implement a landmark Google DeepMind research paper. 🕹️ It codes the reinforcement learning algorithm, visualizes the training live and even debugs errors. ↓

Google DeepMind

369,902 Aufrufe • vor 1 Jahr

You might think AI is stealing art but it's not. It's learning and imagining something entirely new. Hear how it does this from the mouth of the AI mother herself, . SHILLR: Thanks for hosting Claire. I'm still thinking about this space.

You might think AI is stealing art but it's not. It's learning and imagining something entirely new. Hear how it does this from the mouth of the AI mother herself, . SHILLR: Thanks for hosting Claire. I'm still thinking about this space.

macki

440,301 Aufrufe • vor 3 Jahren

Yeah sex is great but have you ever been working on a reinforcement learning project and had multiple claudes tell you that the dataset you've been scraping is incredible?

Yeah sex is great but have you ever been working on a reinforcement learning project and had multiple claudes tell you that the dataset you've been scraping is incredible?

Sterling Crispin 🕊️

51,160 Aufrufe • vor 4 Monaten

8. You need a growth mindset. This is something that amazes me about Larry Williams! even at 81 yrs old, he is still striving to learn more about the markets and improve his edge. You can never stop learning!

8. You need a growth mindset. This is something that amazes me about Larry Williams! even at 81 yrs old, he is still striving to learn more about the markets and improve his edge. You can never stop learning!

TraderTJT

45,195 Aufrufe • vor 2 Jahren