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。

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

56,112 subscribers

164,997 次观看 • 2 年前 •via X (Twitter)

科学技术 #machinelearning #ai

Anya Rossi• Live Now

Private livecam show

10 条评论

Roya 的头像

Roya2 年前

Thank you, the hype made me go back read old papers 😅

Chinonso 的头像

Chinonso2 年前

Thanks, @eigensteve. Just like Q-learning, I guess DQN is also an off-policy TD? Can we also classify the Deep Q-learning as a Model-free method of RL?

Steven Brunton 的头像

Steven Brunton2 年前

You’re welcome. Yes, that is right.

Firstinbattle 的头像

Firstinbattle2 年前

Probably a silly question but does this only work on finite games or can it work on infinite as well? In other words does theta depend on the boundary space of the game.

Ｍｙｓｔｉｑｕｅ的头像

Ｍｙｓｔｉｑｕｅ2 年前

You should do one for Proximal Policy Optimization.

AIBrilliance 的头像

AIBrilliance2 年前

Absolutely enjoying the buzz around Q-learning! Thanks for sharing the insightful video on Deep Reinforcement Learning and Deep Q Learning. 🚀 #machinelearning #ai

RSR 的头像

RSR2 年前

Are you chatgpt or are you seeking viewers ? This is very old man.

Alexey Balandin 的头像

Alexey Balandin2 年前

Wow, this looks like a really well made YouTube course with a lot of high quality explanations. Thank you a lot for your dedication!

UrfaGundem 的头像

UrfaGundem2 年前

Does Q learning has anything to do with quantum?

Statistically Insignificant 的头像

Statistically Insignificant2 年前

What about A*? Havent seen ppl jumping on it

相关视频

A free MIT course about deep learning, 2026 edition: Here, MIT CSAIL researcher Alexander Amini discusses the differences between supervised, unsupervised, & reinforcement learning approaches (Lecture 5).

A free MIT course about deep learning, 2026 edition: Here, MIT CSAIL researcher Alexander Amini discusses the differences between supervised, unsupervised, & reinforcement learning approaches (Lecture 5).

MIT CSAIL

17,457 次观看 • 28 天前

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:

AK

293,341 次观看 • 3 年前

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Jousef Murad

433,149 次观看 • 2 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 • 6 个月前

happy #TransDayOfVisibility here's a clip of my buddy cypress from vrchat learning about it for the first time

Sensitive content

happy #TransDayOfVisibility here's a clip of my buddy cypress from vrchat learning about it for the first time

Marlon

174,589 次观看 • 1 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 )

230,792 次观看 • 2 个月前

They're learning, we're all learning. Watch this to see what the cast picked up about Mzansi while filming. #ShakaiLembeMzansi

They're learning, we're all learning. Watch this to see what the cast picked up about Mzansi while filming. #ShakaiLembeMzansi

Mzansi Magic

11,507 次观看 • 3 年前

Miniature humanoid robots master a simplified soccer game using Deep Reinforcement Learning, showcasing surprising agility, quick fall recovery, and strategic understanding of the game. #engineering

Miniature humanoid robots master a simplified soccer game using Deep Reinforcement Learning, showcasing surprising agility, quick fall recovery, and strategic understanding of the game. #engineering

Interesting Engineering

75,943 次观看 • 3 年前

Years of reinforcement learning in one clip: Atlas pulls off a cartwheel-to-backflip combo with perfect balance.

Years of reinforcement learning in one clip: Atlas pulls off a cartwheel-to-backflip combo with perfect balance.

Big Brain AI

91,525 次观看 • 2 个月前

Deep learning works extraordinarily well. And we still largely don't know why. A new paper from Jamie Simon, Daniel Kunin, and 12 co-authors argues that a scientific theory of deep learning is emerging, and coins a name for the emerging field: learning mechanics. We sat down with Jamie and Dan on Generally Intelligent to talk about what a physics of deep learning would actually look like, why now, and what's left to figure out. 3:05 Learning mechanics as the physics to mechanistic interpretability's biology 4:13 Why deep learning needs a theory 7:07 Why deep learning is uniquely hard to engineer 12:11 How a week in the woods became a paper 25:59 The barrier to theory isn't opacity, but complexity 36:26 Deep learning's first gas law 47:22 Why more particles makes the problem easier 56:22 The discretization hypothesis 1:01:50 The strongest signal that a compact theory exists 1:05:07 The Platonic Representation Hypothesis 1:15:41 Why learning mechanics and mech interp need each other 1:25:29 Theory as safety infrastructure

Deep learning works extraordinarily well. And we still largely don't know why. A new paper from Jamie Simon, Daniel Kunin, and 12 co-authors argues that a scientific theory of deep learning is emerging, and coins a name for the emerging field: learning mechanics. We sat down with Jamie and Dan on Generally Intelligent to talk about what a physics of deep learning would actually look like, why now, and what's left to figure out. 3:05 Learning mechanics as the physics to mechanistic interpretability's biology 4:13 Why deep learning needs a theory 7:07 Why deep learning is uniquely hard to engineer 12:11 How a week in the woods became a paper 25:59 The barrier to theory isn't opacity, but complexity 36:26 Deep learning's first gas law 47:22 Why more particles makes the problem easier 56:22 The discretization hypothesis 1:01:50 The strongest signal that a compact theory exists 1:05:07 The Platonic Representation Hypothesis 1:15:41 Why learning mechanics and mech interp need each other 1:25:29 Theory as safety infrastructure

Imbue

18,081 次观看 • 2 个月前

Excited to share Unit 10, the finale of my latest course! 🎉 My aim is to provide a modern take on learning deep learning & AI using open-source libraries. And I hope you enjoyed the journey from backpropagation to implementing LLMs in PyTorch!

Excited to share Unit 10, the finale of my latest course! 🎉 My aim is to provide a modern take on learning deep learning & AI using open-source libraries. And I hope you enjoyed the journey from backpropagation to implementing LLMs in PyTorch!

Sebastian Raschka

69,415 次观看 • 3 年前

Here's a reference video for folks still learning the language:

Here's a reference video for folks still learning the language:

F'ortuna Favore

918,601 次观看 • 2 年前

Ever wonder how driverless race cars see cones on a track 🤔 👉 See more about deep learning for formula student driverless scenarios:

Ever wonder how driverless race cars see cones on a track 🤔 👉 See more about deep learning for formula student driverless scenarios:

MATLAB

28,640 次观看 • 6 个月前

Reinforcement learning is mind-blowing! Here's a reinforcement learning agent that mastered Breakout and is playing at a superhuman level (score 350+). The crazy part: We didn't write the code or the pipeline. NEO, the first autonomous AI Engineer, did it. From a prompt! It trained over 24 million steps. Evaluated itself. Iterated. Everything under 50 minutes. NEO designed the environment, the reward function, and the entire pipeline. Agentic AI is here!

Reinforcement learning is mind-blowing! Here's a reinforcement learning agent that mastered Breakout and is playing at a superhuman level (score 350+). The crazy part: We didn't write the code or the pipeline. NEO, the first autonomous AI Engineer, did it. From a prompt! It trained over 24 million steps. Evaluated itself. Iterated. Everything under 50 minutes. NEO designed the environment, the reward function, and the entire pipeline. Agentic AI is here!

Santiago

21,701 次观看 • 7 个月前

Q&A #4: How I Approach Learning in Other Domains How I've personally applied the Math Academy learning approach to areas outside of math (specifically biology and music).

Q&A #4: How I Approach Learning in Other Domains How I've personally applied the Math Academy learning approach to areas outside of math (specifically biology and music).

Justin Skycak

15,965 次观看 • 10 个月前

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉

Amazon Web Services

113,245 次观看 • 3 年前

🤯 30.8 BILLION cyberattacks stopped DAILY! How? Precision AI (ML+Deep Learning+Gen AI). Why? Because Gen AI alone hallucinates and cybersecurity demands accuracy. From metadata analysis to deep learning, & now Precision AI,Palo Alto Networks Senior Vice President and GM, Anand Oswal (Anand Oswal) explains how the next evolution of AI is stopping 9M NEW attacks daily. #mwc25 Watch the full video here:

🤯 30.8 BILLION cyberattacks stopped DAILY! How? Precision AI (ML+Deep Learning+Gen AI). Why? Because Gen AI alone hallucinates and cybersecurity demands accuracy. From metadata analysis to deep learning, & now Precision AI,Palo Alto Networks Senior Vice President and GM, Anand Oswal (Anand Oswal) explains how the next evolution of AI is stopping 9M NEW attacks daily. #mwc25 Watch the full video here:

Six Five Media

30,579 次观看 • 1 年前

🚨 BREAKING: Language learning just entered its AI era. Meet Midoo AI — the world’s first AI language learning agent. Not another templated app. Not static flashcards. This is immersive, personalized, agentic learning. Here’s what makes it a game-changer 👇

🚨 BREAKING: Language learning just entered its AI era. Meet Midoo AI — the world’s first AI language learning agent. Not another templated app. Not static flashcards. This is immersive, personalized, agentic learning. Here’s what makes it a game-changer 👇

Pradeep Pandey

59,455 次观看 • 10 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