Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Mondo's Beni ( may look cute, but there is a serious learning stack inside. It can perform flips, navigate autonomously, and track moving subjects. The secret is reinforcement learning: Beni practices at massive scale in simulation, optimizing its controller through millions of virtual trials before entering the real world.... show more

Shuo Yang

5,000 subscribers

30,698 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This is a demonstration video of in-hand object rotation with new Torobo Hand. By leveraging large-scale parallel reinforcement learning in NVIDIA Isaac Sim, the learned policy can perform object manipulation in MuJoCo and on the real robot without any additional training.

This is a demonstration video of in-hand object rotation with new Torobo Hand. By leveraging large-scale parallel reinforcement learning in NVIDIA Isaac Sim, the learned policy can perform object manipulation in MuJoCo and on the real robot without any additional training.

東京ロボティクス株式会社

10,909 views • 1 year ago

The best way to get robust, high-quality robot performance is through reinforcement learning; but RL in either the real world or a traditional simulation has lots of limitations. Instead, Jiazhi Yang in RISE does RL in a compositional world model. Learn more ->

The best way to get robust, high-quality robot performance is through reinforcement learning; but RL in either the real world or a traditional simulation has lots of limitations. Instead, Jiazhi Yang in RISE does RL in a compositional world model. Learn more ->

Chris Paxton

34,102 views • 2 months ago

Today we present Morpheus, a persistent enterprise simulation platform designed to make Continual Learning a reality. Morpheus is the world’s first real world Reinforcement Learning environment. Every Reinforcement Learning environment operates in the game world. Benchmarks like Atari, OpenAI Gym, MuJoCo, and Procgen are all small, game-like worlds that reset every few minutes. But the real world never resets. A business keeps running and evolving everyday. We tested how frontier LLMs would perform in realistic and dynamic business environments 🧬on Morpheus. The main conclusion was that LLMs are not continual learners. 🧵Here’s how we did it and what we learned:

Today we present Morpheus, a persistent enterprise simulation platform designed to make Continual Learning a reality. Morpheus is the world’s first real world Reinforcement Learning environment. Every Reinforcement Learning environment operates in the game world. Benchmarks like Atari, OpenAI Gym, MuJoCo, and Procgen are all small, game-like worlds that reset every few minutes. But the real world never resets. A business keeps running and evolving everyday. We tested how frontier LLMs would perform in realistic and dynamic business environments 🧬on Morpheus. The main conclusion was that LLMs are not continual learners. 🧵Here’s how we did it and what we learned:

Skyfall AI

268,132 views • 1 month ago

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,772 views • 2 months ago

Just months after its debut, Atlas is proving why it is the world’s most capable and dynamic humanoid robot, ready for real work. Lifting a mini-fridge is a feat of strength, but the true breakthrough is in the underlying reinforcement learning and controls systems.

Just months after its debut, Atlas is proving why it is the world’s most capable and dynamic humanoid robot, ready for real work. Lifting a mini-fridge is a feat of strength, but the true breakthrough is in the underlying reinforcement learning and controls systems.

Boston Dynamics

41,726 views • 3 months ago

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

18,813 views • 7 months ago

Bittensor is the main thing I’m watching at Proof of Talk. The subnet conversation is moving from CT speculation into real institutional interest now. Decentralized intelligence, open markets for machine learning, subnet economies, this is the part of crypto that actually feels like it can matter at scale. Most people still underestimate how big that shift is. Feels like $TAO is entering its serious capital era.

Bittensor is the main thing I’m watching at Proof of Talk. The subnet conversation is moving from CT speculation into real institutional interest now. Decentralized intelligence, open markets for machine learning, subnet economies, this is the part of crypto that actually feels like it can matter at scale. Most people still underestimate how big that shift is. Feels like $TAO is entering its serious capital era.

nordin.eth

11,196 views • 3 months ago

See Spot perform dynamic whole-body manipulation. Using a combination of reinforcement learning (RL) and sampling-based control, the robot is able to autonomously drag, roll, and stack tires weighing 15 kg (33 lb), well above its maximum arm lift capacity. Learn more about coordinating locomotion and manipulation processes:

See Spot perform dynamic whole-body manipulation. Using a combination of reinforcement learning (RL) and sampling-based control, the robot is able to autonomously drag, roll, and stack tires weighing 15 kg (33 lb), well above its maximum arm lift capacity. Learn more about coordinating locomotion and manipulation processes:

RAI Institute

87,583 views • 10 months ago

Wow. This is crazy. A developer trained an AI agent in simulation and deployed it onto a real robotic air hockey table using reinforcement learning. This robot can track the puck with millimeter-level accuracy and react in roughly 20 milliseconds, fast enough to challenge even skilled human players. We’re moving from robots that follow programmed rules to machines that learn strategies in simulation and execute them in the physical world.

Wow. This is crazy. A developer trained an AI agent in simulation and deployed it onto a real robotic air hockey table using reinforcement learning. This robot can track the puck with millimeter-level accuracy and react in roughly 20 milliseconds, fast enough to challenge even skilled human players. We’re moving from robots that follow programmed rules to machines that learn strategies in simulation and execute them in the physical world.

SciTech Era

1,585,178 views • 3 months ago

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 views • 1 year ago

Mark Zuckerberg and Priscilla Chan say virtual cells could change how science takes risk, letting researchers test bold ideas in simulation before entering the wet lab. “The promise of being able to do virtual biology… is you can actually take on riskier ideas.” “If you had a virtual cell model… you could actually then start testing it and tinkering on the computational side… and actually see if there is promise doing the experiments in silico before you make the time and money investment in the wet lab.”

Mark Zuckerberg and Priscilla Chan say virtual cells could change how science takes risk, letting researchers test bold ideas in simulation before entering the wet lab. “The promise of being able to do virtual biology… is you can actually take on riskier ideas.” “If you had a virtual cell model… you could actually then start testing it and tinkering on the computational side… and actually see if there is promise doing the experiments in silico before you make the time and money investment in the wet lab.”

a16z

44,009 views • 9 months ago

These are not CGI. Reinforcement learning is so back. When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning algorithms that can master both the world of bits and the world of atoms. Give me a reward function, and I shall move the world. 2025, Year of RL.

These are not CGI. Reinforcement learning is so back. When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning algorithms that can master both the world of bits and the world of atoms. Give me a reward function, and I shall move the world. 2025, Year of RL.

Jim Fan

356,840 views • 1 year ago

Noble Machines' Moby robot hauling a 50 lb crate. The whole-body control (WBC) is the physical foundation of the learning stack. It absorbs payload variation, contact response, and center-of-mass shifts in real time at the control layer and enabled cleaner data-focused learning

Noble Machines' Moby robot hauling a 50 lb crate. The whole-body control (WBC) is the physical foundation of the learning stack. It absorbs payload variation, contact response, and center-of-mass shifts in real time at the control layer and enabled cleaner data-focused learning

The Humanoid Hub

17,482 views • 3 months ago

Weekends are for research. Inside OptimAI labs, we’ve been pushing agents beyond the screen. A first glimpse of OptimAI Prime. Not just agents that think, but agents that operate. Learning through reinforcement, coordinating across the network, and executing in real-world environments. From digital workflows → to physical actions. This is the next step for the agent-native internet.🤖 Still early. But already in motion.

Weekends are for research. Inside OptimAI labs, we’ve been pushing agents beyond the screen. A first glimpse of OptimAI Prime. Not just agents that think, but agents that operate. Learning through reinforcement, coordinating across the network, and executing in real-world environments. From digital workflows → to physical actions. This is the next step for the agent-native internet.🤖 Still early. But already in motion.

OptimAI Network

20,846 views • 4 months ago

Joscha Bach says consciousness is not a mysterious extra ingredient. It is a model of what it would be like if you existed. The self is virtual by definition. It can only run inside a system capable of simulation. This does not make it less real. It makes it substrate-dependent in exactly the way software is. The hard problem may not be hard. It may be a category error about where to look.

Joscha Bach says consciousness is not a mysterious extra ingredient. It is a model of what it would be like if you existed. The self is virtual by definition. It can only run inside a system capable of simulation. This does not make it less real. It makes it substrate-dependent in exactly the way software is. The hard problem may not be hard. It may be a category error about where to look.

vitrupo

39,202 views • 5 months ago

This is a neural network flying a drone at extremely high speed, beating human champions in FPV drone racing. - Reinforcement learning as a tool is so marvelously versatile. It's able to solve both fast, reactive tasks and slow, deliberate tasks (ChatGPT RLHF). - Trained in large-scale simulation, finetuned in real world - I believe this is the paradigm that will get us to generalist robot some day. Published on Nature's cover, "Champion-Level Drone Racing using Deep Reinforcement Learning." Authors: Elia Kaufmann, Leonard Bauersfeld, Antonio Loquercio, Matthias Müller, Vladlen Koltun & Davide Scaramuzza

This is a neural network flying a drone at extremely high speed, beating human champions in FPV drone racing. - Reinforcement learning as a tool is so marvelously versatile. It's able to solve both fast, reactive tasks and slow, deliberate tasks (ChatGPT RLHF). - Trained in large-scale simulation, finetuned in real world - I believe this is the paradigm that will get us to generalist robot some day. Published on Nature's cover, "Champion-Level Drone Racing using Deep Reinforcement Learning." Authors: Elia Kaufmann, Leonard Bauersfeld, Antonio Loquercio, Matthias Müller, Vladlen Koltun & Davide Scaramuzza

Jim Fan

598,828 views • 3 years ago

The reason $META is a winner in the AI economy is that it can embed AI directly into products already used by billions of consumers and millions of businesses. This lets them turn model improvements into better ads, WhatsApp agents, AI glasses, recommendation systems and creative tools almost immediately. Those products may look separate but they all run on same infrastructure, models, proprietary data and distribution creating a shared AI stack that can compound across multiple revenue streams.

The reason $META is a winner in the AI economy is that it can embed AI directly into products already used by billions of consumers and millions of businesses. This lets them turn model improvements into better ads, WhatsApp agents, AI glasses, recommendation systems and creative tools almost immediately. Those products may look separate but they all run on same infrastructure, models, proprietary data and distribution creating a shared AI stack that can compound across multiple revenue streams.

Shay Boloor

71,172 views • 1 month ago

[1/16] The real world is large, and we want our AI models to operate on the scale of reality. Over the past two years, my colleagues and I have developed fVDB, a deep learning framework for large-scale, high performance spatial intelligence. We finally announced this work at SIGGRAPH and have released the framework in early access. Here’s a small tour of what fVDB is, and what we’ve used it to do.

[1/16] The real world is large, and we want our AI models to operate on the scale of reality. Over the past two years, my colleagues and I have developed fVDB, a deep learning framework for large-scale, high performance spatial intelligence. We finally announced this work at SIGGRAPH and have released the framework in early access. Here’s a small tour of what fVDB is, and what we’ve used it to do.

Francis Williams

34,026 views • 2 years ago

Watch: Learning Hindi won’t erase Tamil. It will open doors. ~ Vijayakanth, a famous Tamil actor. The propaganda by certain political parties says “If we learn Hindi, Tamil Nadu will lose its identity and turn into Hindi.” This fear is used to oppose learning the language. Tamil is our breath, our pride. But learning other languages is also important. Our brothers and sisters in Delhi and Mumbai learned Hindi to earn a living and support their families. Learning Hindi from childhood can open opportunities. Yet today, DMK is placing restrictions on Tamilians learning Hindi and spreading hatred towards the language. Tamil is like a mother for Tamilians, and Hindi is a mother for millions. Both deserve respect🙏🏻

Watch: Learning Hindi won’t erase Tamil. It will open doors. ~ Vijayakanth, a famous Tamil actor. The propaganda by certain political parties says “If we learn Hindi, Tamil Nadu will lose its identity and turn into Hindi.” This fear is used to oppose learning the language. Tamil is our breath, our pride. But learning other languages is also important. Our brothers and sisters in Delhi and Mumbai learned Hindi to earn a living and support their families. Learning Hindi from childhood can open opportunities. Yet today, DMK is placing restrictions on Tamilians learning Hindi and spreading hatred towards the language. Tamil is like a mother for Tamilians, and Hindi is a mother for millions. Both deserve respect🙏🏻

FalconUpdatesHQ

75,047 views • 10 months ago

The CIA Headquarters in McLean, Virginia is one of the most secure and secretive compounds in the world. But tucked away on the land is a century-old farmhouse with a history of its own. Olivia Gazis got a never-before-seen look inside.

The CIA Headquarters in McLean, Virginia is one of the most secure and secretive compounds in the world. But tucked away on the land is a century-old farmhouse with a history of its own. Olivia Gazis got a never-before-seen look inside.

CBS Saturday Morning

391,224 views • 2 years ago