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。

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

Ajeet ( opensox.ai )

16,048 subscribers

228,651 次观看 • 1 个月前 •via X (Twitter)

教育科学技术

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

Learn how to use G-PAD's from with a guest cameo from SuperHorrorBro Play the brand new demo on Steam today!

Don't Fret - NEW DEMO OUT NOW!

21,175 次观看 • 11 天前

#Jaguars HC Liam Coen on how Bhayshul Tuten is looking: “He put the ball on the ground today, that kinda stands out… Good learning experience, first time in a live setting in the National Football League on your first carry — hopefully you learn something from that moment.”

#Jaguars HC Liam Coen on how Bhayshul Tuten is looking: “He put the ball on the ground today, that kinda stands out… Good learning experience, first time in a live setting in the National Football League on your first carry — hopefully you learn something from that moment.”

The Coachspeak Index

1,247,694 次观看 • 1 年前

how to understand a codebase from the first principles. (example with a real production codebase)

how to understand a codebase from the first principles. (example with a real production codebase)

Ajeet ( opensox.ai )

24,435 次观看 • 1 个月前

We are delighted to announce that the Animator’s Survival Kit Animated is now live on Bloomsbury Video Library: Learn the principles of sophisticated animation with videos from multi-Oscar winner Richard Williams, available to stream for the first time.

We are delighted to announce that the Animator’s Survival Kit Animated is now live on Bloomsbury Video Library: Learn the principles of sophisticated animation with videos from multi-Oscar winner Richard Williams, available to stream for the first time.

Bloomsbury Digital Resources

22,150 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

164,982 次观看 • 2 年前

I trained a humanoid robot to play famous anime openings on the piano with reinforcement learning (Attack on Titan, Evangelion, SAO, and more) how I did it + surprising discoveries in thread🧵

I trained a humanoid robot to play famous anime openings on the piano with reinforcement learning (Attack on Titan, Evangelion, SAO, and more) how I did it + surprising discoveries in thread🧵

anandmaj

24,589 次观看 • 1 年前

John Mayer’s approach to learning the guitar is a 104-second masterclass on how to learn anything:

John Mayer’s approach to learning the guitar is a 104-second masterclass on how to learn anything:

Billy Oppenheimer

783,672 次观看 • 3 年前

How To Turn A Girl On (Live Demo)

Sensitive content

How To Turn A Girl On (Live Demo)

PWF | Dating Expert

85,478 次观看 • 11 天前

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

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

Dennis Gustafsson

22,362 次观看 • 9 个月前

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

46,302 次观看 • 1 年前

6/ Josh on learning from others. He explains a visualization technique to 100x your learning curve. How fast could we learn if we harnessed this to its full potential?

6/ Josh on learning from others. He explains a visualization technique to 100x your learning curve. How fast could we learn if we harnessed this to its full potential?

Martin

50,493 次观看 • 1 年前

4/ Claude Voyager -🏅Code award Claude connected to a code environment that enables it to create its own tools on the fly Live demo of Claude learning how to query Stripe on its own

4/ Claude Voyager -🏅Code award Claude connected to a code environment that enables it to create its own tools on the fly Live demo of Claude learning how to query Stripe on its own

Alex Reibman 🖇️

11,178 次观看 • 1 年前

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

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

Dan Advantage

41,895 次观看 • 6 个月前

A step by step tutorial on Recursion. Learn how to inscribe from a homie. The full version will be live: on Beta soon!!!

A step by step tutorial on Recursion. Learn how to inscribe from a homie. The full version will be live: on Beta soon!!!

8Bit🍊

35,078 次观看 • 2 年前

Learning something new 👀 Kimi and George learn how to write their names in Arabic, and a few phrases too! 🗣️

Learning something new 👀 Kimi and George learn how to write their names in Arabic, and a few phrases too! 🗣️

Mercedes-AMG PETRONAS F1 Team

121,476 次观看 • 1 年前

How to actually learn something from Social interactions

How to actually learn something from Social interactions

Neo

134,911 次观看 • 1 年前

NVIDIA's Jim Fan has verified from reliable sources that the video by EngineAI is a real robot demo and not CGI. The controller is a neural net trained in the NVIDIA Isaac simulator using reinforcement learning. There’s also another video from a different angle.

NVIDIA's Jim Fan has verified from reliable sources that the video by EngineAI is a real robot demo and not CGI. The controller is a neural net trained in the NVIDIA Isaac simulator using reinforcement learning. There’s also another video from a different angle.

The Humanoid Hub

148,535 次观看 • 1 年前

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 • 5 个月前

//SPOILERS i love how the song Live and Learn actually has a purpose in the movie,, its not just fan service,, it MEANS and REPRESENTS something. only to shadow at first, but it becomes something they both learn and embrace by the climax. absolute cinema

//SPOILERS i love how the song Live and Learn actually has a purpose in the movie,, its not just fan service,, it MEANS and REPRESENTS something. only to shadow at first, but it becomes something they both learn and embrace by the climax. absolute cinema

chillaxin🍳

94,672 次观看 • 1 年前

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

18,541 次观看 • 5 个月前