正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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 次观看 • 10 个月前

An interesting example of reinforcement learning.

An interesting example of reinforcement learning.

Historic Vids

1,564,042 次观看 • 3 年前

2026 is about learning something new

2026 is about learning something new

alec

17,678 次观看 • 10 个月前

An Interesting example of Reinforcement learning!! 🐓

An Interesting example of Reinforcement learning!! 🐓

OpenMoon

7,059,237 次观看 • 2 年前

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

76,796 次观看 • 1 年前

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

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

MachinePix

16,995,824 次观看 • 3 年前

There is training and there is training. Realism - the drone WILL hit you in the face if you do not shoot it down - brings fear, maximum awareness and deep learning. Shooting at a paper box, is a starting point, but it is not 'learning'.

There is training and there is training. Realism - the drone WILL hit you in the face if you do not shoot it down - brings fear, maximum awareness and deep learning. Shooting at a paper box, is a starting point, but it is not 'learning'.

Luc Rombout

189,963 次观看 • 1 个月前

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

1,324,577 次观看 • 3 个月前

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

20,227 次观看 • 1 年前

Its nice to see the recent excitement around Q-learning! Here's a clip from a video all about Deep Reinforcement Learning, including Deep Q Learning #machinelearning #ai

Its nice to see the recent excitement around Q-learning! Here's a clip from a video all about Deep Reinforcement Learning, including Deep Q Learning #machinelearning #ai

Steven Brunton

165,202 次观看 • 2 年前

He’s still here… so I guess he’s learning. But is he learning fast enough?

Sensitive content

He’s still here… so I guess he’s learning. But is he learning fast enough?

Miss Maya

10,779 次观看 • 2 个月前

Reinforcement learning

Reinforcement learning

Massimo

3,407,939 次观看 • 2 年前

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

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

Humanoid

11,571 次观看 • 20 天前

I love that Ben White clearly is so passionate about learning and improving into his fifth season at Arsenal

I love that Ben White clearly is so passionate about learning and improving into his fifth season at Arsenal

Av

382,841 次观看 • 2 个月前

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

279,429 次观看 • 1 年前

In this demo, Beam was prompted to create a 3D game in p5.js where an astronaut is free falling towards earth and must dodge or hit asteroids. Although Beam is not multimodal, its reinforcement learning (RL) training allows it to generalize across domains like gameplay.

In this demo, Beam was prompted to create a 3D game in p5.js where an astronaut is free falling towards earth and must dodge or hit asteroids. Although Beam is not multimodal, its reinforcement learning (RL) training allows it to generalize across domains like gameplay.

Reflection

50,852 次观看 • 28 天前

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

68,317 次观看 • 1 年前

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

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

AK

838,293 次观看 • 3 年前

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

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

Ajeet ( opensox.ai )

235,889 次观看 • 6 个月前