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。

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... show more

Jim Fan

499,977 subscribers

598,669 次观看 • 3 年前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

10 条评论

Jim Fan 的头像

Jim Fan3 年前

Original post from the author:

Jeff Holmes 的头像

Jeff Holmes3 年前

Who's building the tiny fly and mosquito catching drone for us?

Amy Robinson Sterling 的头像

Amy Robinson Sterling3 年前

one step closer to house robots

Per-Anders Edwards 的头像

Per-Anders Edwards3 年前

There’s a positive use for deliveries, but there are oh so many more negative uses and you can be sure the DoD and domestic enforcement are going to use every last one of them. So well done that team I guess, you achieved your goal and now you get to reap your reward.

Dave Lavallee 的头像

Dave Lavallee3 年前

The implications of this achievement are just scratching the surface of what will be possible in the future. Kudos to the team.

Harri Hakulinen 🇫🇮🇺🇦🇪🇺 的头像

Harri Hakulinen 🇫🇮🇺🇦🇪🇺3 年前

The (near) future of warplanes / wingmans..

𝙀𝙧𝙣𝙖 𝙆𝙧𝙪𝙢𝙗𝙖𝙘𝙝 的头像

𝙀𝙧𝙣𝙖 𝙆𝙧𝙪𝙢𝙗𝙖𝙘𝙝3 年前

When I saw this simulation it reminded me of Harry Potter movie when Harry playing soccer with the broomstick 🧹. Probably NIMBUS1000 is good name for super high speed drone . Just like Harry’s broomsticks.

Lucas Cooper-Bey 的头像

Lucas Cooper-Bey3 年前

Well it’s been fun. Hope AGI is stoked on humans

Syrsly (bsky:syrsly.com) 的头像

Syrsly (bsky:syrsly.com)3 年前

They're essentially handicapping the race course with standard track shapes instead of random objects. I'm sure it would require a lot more training to handle boxes of different colors, different lighting conditions, rain, triangles... you get the idea.

Φιμπονάτσι 的头像

Φιμπονάτσι3 年前

ww3 will be fought with drones/lasers/ai no question

相关视频

End-to-end neural networks racing drones in Abu Dhabi! 🚁 Check out the drone racing team from Delft University of Technology! A completely end-to-end neural network solution, from pixels to direct motor commands. No Kalman filters. No computer vision feature detectors. Just neurons flying the drone. The challenge is extreme. These drones fly at high speeds and need split-second decisions with minimal onboard resources: a single rolling-shutter camera and an IMU. Their approach is called SkyDreamer, based on the Dreamer-v3 reinforcement learning algorithm. First, a world model is trained in simulation. Then, the neural network learns how to fly in its dreams through reinforcement learning. The network's internal state can be read out to see where it thinks it is on the track or how fast it's going. Even better, the drone estimates some of its own body characteristics during flight, like the camera angle relative to the body, eliminating time-consuming manual calibration. The system uses only a single camera and the gyros from the IMU, ignoring the accelerometers, just like human FPV pilots do. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

End-to-end neural networks racing drones in Abu Dhabi! 🚁 Check out the drone racing team from Delft University of Technology! A completely end-to-end neural network solution, from pixels to direct motor commands. No Kalman filters. No computer vision feature detectors. Just neurons flying the drone. The challenge is extreme. These drones fly at high speeds and need split-second decisions with minimal onboard resources: a single rolling-shutter camera and an IMU. Their approach is called SkyDreamer, based on the Dreamer-v3 reinforcement learning algorithm. First, a world model is trained in simulation. Then, the neural network learns how to fly in its dreams through reinforcement learning. The network's internal state can be read out to see where it thinks it is on the track or how fast it's going. Even better, the drone estimates some of its own body characteristics during flight, like the camera angle relative to the body, eliminating time-consuming manual calibration. The system uses only a single camera and the gyros from the IMU, ignoring the accelerometers, just like human FPV pilots do. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

207,379 次观看 • 6 个月前

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

18,813 次观看 • 7 个月前

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

1,584,984 次观看 • 2 个月前

We are thrilled to share our breakthrough research on "Agile Flight from Pixels without State Estimation," to be presented and live-demonstrated at #RSS2024 next week! You heard well: no state estimation means no explicit visual localization, no SLAM, no VIO, and no IMU! Paper: Video (Narrated): Last year, we demonstrated that #ReinforcementLearning (RL) policies could outperform world-champion drone-racing pilots using the same quadrotor hardware; however, unlike human pilots, these policies continuously estimated an explicit state from known gate positions, the camera feed, and inertial measurements (IMU). In this new work, we tackle the challenge of learning vision-based drone racing using an end-to-end reinforcement learning approach that eliminates the need for IMU data or explicit state estimation. Like professional pilots, we go directly from images to control commands. The training is facilitated by an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use an appropriate sensor representation, which can be efficiently simulated during training without rendering images. We achieve agile flight at speeds up to 40 km/h with accelerations up to 2 g's. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments. Besides the paper presentation, we will also give a live demo next Tuesday and Wednesday between and hrs at TU Delft: Reference: Ismail Geles*, Leonard Bauersfeld*, Angel Romero, Jiaxu Xing, Davide Scaramuzza "Demonstrating Agile Flight from Pixels without State Estimation" Robotics: Science and Systems (RSS), 2024. Kudos to Ismail Geles Leonard Bauersfeld Ángel Romero Jiaxu Xing! University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)

We are thrilled to share our breakthrough research on "Agile Flight from Pixels without State Estimation," to be presented and live-demonstrated at #RSS2024 next week! You heard well: no state estimation means no explicit visual localization, no SLAM, no VIO, and no IMU! Paper: Video (Narrated): Last year, we demonstrated that #ReinforcementLearning (RL) policies could outperform world-champion drone-racing pilots using the same quadrotor hardware; however, unlike human pilots, these policies continuously estimated an explicit state from known gate positions, the camera feed, and inertial measurements (IMU). In this new work, we tackle the challenge of learning vision-based drone racing using an end-to-end reinforcement learning approach that eliminates the need for IMU data or explicit state estimation. Like professional pilots, we go directly from images to control commands. The training is facilitated by an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use an appropriate sensor representation, which can be efficiently simulated during training without rendering images. We achieve agile flight at speeds up to 40 km/h with accelerations up to 2 g's. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments. Besides the paper presentation, we will also give a live demo next Tuesday and Wednesday between and hrs at TU Delft: Reference: Ismail Geles, Leonard Bauersfeld, Angel Romero, Jiaxu Xing, Davide Scaramuzza "Demonstrating Agile Flight from Pixels without State Estimation" Robotics: Science and Systems (RSS), 2024. Kudos to Ismail Geles Leonard Bauersfeld Ángel Romero Jiaxu Xing! University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)

Davide Scaramuzza

27,917 次观看 • 2 年前

This robot learned to walk without ever actually walking in the real world Like in The Matrix (“I know Kung Fu”) it learned quickly just by SIMULATING walking. It practiced "in its head" Ok so what? Do you realize how suddenly our lil chatbots might go from blinking cursors to very real things? Some people assume that we’ll see robots in the real world slowly getting better over years or decades !BUT! if they can learn 10000x faster via simulation, they could they could blow our expectations out of the water. For example, an autonomous killer drone (like the ones already deployed in Ukraine) could get 1,000 years of aiming experience in 1 hour of human time. It would never miss. (More technically, this is a humanoid transformer that was trained with large-scale reinforcement learning in simulation. It was deployed to the real world zero-shot.)

This robot learned to walk without ever actually walking in the real world Like in The Matrix (“I know Kung Fu”) it learned quickly just by SIMULATING walking. It practiced "in its head" Ok so what? Do you realize how suddenly our lil chatbots might go from blinking cursors to very real things? Some people assume that we’ll see robots in the real world slowly getting better over years or decades !BUT! if they can learn 10000x faster via simulation, they could they could blow our expectations out of the water. For example, an autonomous killer drone (like the ones already deployed in Ukraine) could get 1,000 years of aiming experience in 1 hour of human time. It would never miss. (More technically, this is a humanoid transformer that was trained with large-scale reinforcement learning in simulation. It was deployed to the real world zero-shot.)

AI Notkilleveryoneism Memes ⏸️

128,995 次观看 • 2 年前

Can an inexpensive, off-the-shelf IMU be the only sensor to estimate the full state (position, velocity, orientation) of a quadrotor flying through a track at high speed and even be on-pair with vision-based localization? The answer is yes, within certain limitations! In this #RAL2023 paper, we propose a learning-based odometry algorithm that couples a model-based filter driven by the inertial measurements with a learning-based module with access to the control commands. Our system outperforms by a large margin the state-of-the-art visual-inertial odometry (#VIO) algorithms and the state-of-the-art learned-inertial odometry algorithm, #TLIO, for the task of drone racing. Additionally, we show that our system is as accurate as a VIO algorithm that uses a camera to localize to a known map of the racing track. The main limitation of our approach is that it cannot generalize to trajectories that have not been seen at training time. However, in drone racing competitions, the track is known beforehand. Human pilots spend hours or even days of practice on the race track before the competition. Similarly, our system can be trained with the data collected during practice time and deployed during the competition. Future work will investigate how to generalize to trajectories not seen at training time. The code is released! Paper: Video: Code: Kudos to Giovanni Cioffi Leonard Bauersfeld Elia Kaufmann European Research Council (ERC) University of Zurich UZH Science UZH Space Hub NCCR Robotics Aerial Core #RAL2023 #IROS2023 #SLAM

Can an inexpensive, off-the-shelf IMU be the only sensor to estimate the full state (position, velocity, orientation) of a quadrotor flying through a track at high speed and even be on-pair with vision-based localization? The answer is yes, within certain limitations! In this #RAL2023 paper, we propose a learning-based odometry algorithm that couples a model-based filter driven by the inertial measurements with a learning-based module with access to the control commands. Our system outperforms by a large margin the state-of-the-art visual-inertial odometry (#VIO) algorithms and the state-of-the-art learned-inertial odometry algorithm, #TLIO, for the task of drone racing. Additionally, we show that our system is as accurate as a VIO algorithm that uses a camera to localize to a known map of the racing track. The main limitation of our approach is that it cannot generalize to trajectories that have not been seen at training time. However, in drone racing competitions, the track is known beforehand. Human pilots spend hours or even days of practice on the race track before the competition. Similarly, our system can be trained with the data collected during practice time and deployed during the competition. Future work will investigate how to generalize to trajectories not seen at training time. The code is released! Paper: Video: Code: Kudos to Giovanni Cioffi Leonard Bauersfeld Elia Kaufmann European Research Council (ERC) University of Zurich UZH Science UZH Space Hub NCCR Robotics Aerial Core #RAL2023 #IROS2023 #SLAM

Davide Scaramuzza

37,061 次观看 • 2 年前

🚨🇺🇸FIGURE ROBOT LEARNS TO WALK IN HOURS Turns out you can teach a robot to walk—if you’ve got a few years to burn in a physics simulator (or a few hours of GPU time). Figure’s team trained a neural network using reinforcement learning to mimic natural human locomotion, and the wild part is it worked on the first try with real hardware. No tuning. No fiddling. Just plug and strut. Thanks to sim-to-real transfer and some sneaky domain randomization, the robot didn’t just wobble out of the lab—it walked like it had somewhere to be. Next up: running. Not terrifying at all. Source: Figure

🚨🇺🇸FIGURE ROBOT LEARNS TO WALK IN HOURS Turns out you can teach a robot to walk—if you’ve got a few years to burn in a physics simulator (or a few hours of GPU time). Figure’s team trained a neural network using reinforcement learning to mimic natural human locomotion, and the wild part is it worked on the first try with real hardware. No tuning. No fiddling. Just plug and strut. Thanks to sim-to-real transfer and some sneaky domain randomization, the robot didn’t just wobble out of the lab—it walked like it had somewhere to be. Next up: running. Not terrifying at all. Source: Figure

Mario Nawfal

117,866 次观看 • 1 年前

I don’t know if we live in a Matrix, but I know for sure that robots will spend most of their lives in simulation. Let machines train machines. I’m excited to introduce DexMimicGen, a massive-scale synthetic data generator that enables a humanoid robot to learn complex skills from only a handful of human demonstrations. Yes, as few as 5! DexMimicGen addresses the biggest pain point in robotics: where do we get data? Unlike with LLMs, where vast amounts of texts are readily available, you cannot simply download motor control signals from the internet. So researchers teleoperate the robots to collect motion data via XR headsets. They have to repeat the same skill over and over and over again, because neural nets are data hungry. This is a very slow and uncomfortable process. At NVIDIA, we believe the majority of high-quality tokens for robot foundation models will come from simulation. What DexMimicGen does is to trade GPU compute time for human time. It takes one motion trajectory from human, and multiplies into 1000s of new trajectories. A robot brain trained on this augmented dataset will generalize far better in the real world. Think of DexMimicGen as a learning signal amplifier. It maps a small dataset to a large (de facto infinite) dataset, using physics simulation in the loop. In this way, we free humans from babysitting the bots all day. The future of robot data is generative. The future of the entire robot learning pipeline will also be generative. 🧵

I don’t know if we live in a Matrix, but I know for sure that robots will spend most of their lives in simulation. Let machines train machines. I’m excited to introduce DexMimicGen, a massive-scale synthetic data generator that enables a humanoid robot to learn complex skills from only a handful of human demonstrations. Yes, as few as 5! DexMimicGen addresses the biggest pain point in robotics: where do we get data? Unlike with LLMs, where vast amounts of texts are readily available, you cannot simply download motor control signals from the internet. So researchers teleoperate the robots to collect motion data via XR headsets. They have to repeat the same skill over and over and over again, because neural nets are data hungry. This is a very slow and uncomfortable process. At NVIDIA, we believe the majority of high-quality tokens for robot foundation models will come from simulation. What DexMimicGen does is to trade GPU compute time for human time. It takes one motion trajectory from human, and multiplies into 1000s of new trajectories. A robot brain trained on this augmented dataset will generalize far better in the real world. Think of DexMimicGen as a learning signal amplifier. It maps a small dataset to a large (de facto infinite) dataset, using physics simulation in the loop. In this way, we free humans from babysitting the bots all day. The future of robot data is generative. The future of the entire robot learning pipeline will also be generative. 🧵

Jim Fan

165,246 次观看 • 1 年前

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

20,434 次观看 • 7 个月前

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Ilir Aliu

18,210 次观看 • 6 个月前

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:

Andrew Ng

86,457 次观看 • 1 年前

Can GPT-4 teach a robot hand to do pen spinning tricks better than you do? I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API! Eureka bridges the gap between high-level reasoning (coding) and low-level motor control. It is a “hybrid-gradient architecture”: a black box, inference-only LLM instructs a white box, learnable neural network. The outer loop runs GPT-4 to refine the reward function (gradient-free), while the inner loop runs reinforcement learning to train a robot controller (gradient-based). We are able to scale up Eureka thanks to IsaacGym, a GPU-accelerated physics simulator that speeds up reality by 1000x. On a benchmark suite of 29 tasks across 10 robots, Eureka rewards outperform expert human-written ones on 83% of the tasks by 52% improvement margin on average. We are surprised that Eureka is able to learn pen spinning tricks, which are very difficult even for CGI artists to animate frame by frame! Eureka also enables a new form of in-context RLHF, which is able to incorporate a human operator’s feedback in natural language to steer and align the reward functions. It can serve as a powerful co-pilot for robot engineers to design sophisticated motor behaviors. As usual, we open-source everything! Welcome you all to check out our video gallery and try the codebase today: Paper: Code: Deep dive with me: 🧵

Can GPT-4 teach a robot hand to do pen spinning tricks better than you do? I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API! Eureka bridges the gap between high-level reasoning (coding) and low-level motor control. It is a “hybrid-gradient architecture”: a black box, inference-only LLM instructs a white box, learnable neural network. The outer loop runs GPT-4 to refine the reward function (gradient-free), while the inner loop runs reinforcement learning to train a robot controller (gradient-based). We are able to scale up Eureka thanks to IsaacGym, a GPU-accelerated physics simulator that speeds up reality by 1000x. On a benchmark suite of 29 tasks across 10 robots, Eureka rewards outperform expert human-written ones on 83% of the tasks by 52% improvement margin on average. We are surprised that Eureka is able to learn pen spinning tricks, which are very difficult even for CGI artists to animate frame by frame! Eureka also enables a new form of in-context RLHF, which is able to incorporate a human operator’s feedback in natural language to steer and align the reward functions. It can serve as a powerful co-pilot for robot engineers to design sophisticated motor behaviors. As usual, we open-source everything! Welcome you all to check out our video gallery and try the codebase today: Paper: Code: Deep dive with me: 🧵

Jim Fan

2,674,348 次观看 • 2 年前

Let's reverse engineer Disney's adorable, lifelike robot! I couldn't find a whitepaper, but this is how I think it's trained: 1. The emotional behaviors are curated by Disney animation artists, keyframe by keyframe. But it cannot be "rendered" directly on the robot because it doesn't take into account the complex real-world physics. 2. Reinforcement learning (RL) is a great tool for training low-level robot controllers. RL needs a reward function to optimize, and it's typically a task reward (e.g. walk in a straight line as fast as possible). The problem is that RL doesn't know what counts as "natural behavior", and often produces weird-looking body postures that somehow still maximize the reward. This is a human alignment problem just like ChatGPT. 3. Enters Adversarial Motion Prior (AMP): a technique that learns the human preference by training a classifier on what we consider "emotional & cute". In GAN literature, this is called a discriminator. Disney artists are good at creating such a dataset. You can then add AMP as an auxiliary reward in simulation to nudge the robot towards desired behaviors. AMP was developed by Peng et al. 2021 and Escontrela et al. 2022. 4. Add lots of data augmentation to make the controller robust to physical disturbances. In RL, it's called "domain randomization". This is a very powerful technique that bridges the gap between simulator and reality. Previously, OpenAI used domain randomization to train a 5-finger robot hand to manipulate a Rubik's Cube: IEEE news article gave hints about the pipeline: Finally, praying for world peace 🙏. I hope robotics like this will bring more joy to the world.

Let's reverse engineer Disney's adorable, lifelike robot! I couldn't find a whitepaper, but this is how I think it's trained: 1. The emotional behaviors are curated by Disney animation artists, keyframe by keyframe. But it cannot be "rendered" directly on the robot because it doesn't take into account the complex real-world physics. 2. Reinforcement learning (RL) is a great tool for training low-level robot controllers. RL needs a reward function to optimize, and it's typically a task reward (e.g. walk in a straight line as fast as possible). The problem is that RL doesn't know what counts as "natural behavior", and often produces weird-looking body postures that somehow still maximize the reward. This is a human alignment problem just like ChatGPT. 3. Enters Adversarial Motion Prior (AMP): a technique that learns the human preference by training a classifier on what we consider "emotional & cute". In GAN literature, this is called a discriminator. Disney artists are good at creating such a dataset. You can then add AMP as an auxiliary reward in simulation to nudge the robot towards desired behaviors. AMP was developed by Peng et al. 2021 and Escontrela et al. 2022. 4. Add lots of data augmentation to make the controller robust to physical disturbances. In RL, it's called "domain randomization". This is a very powerful technique that bridges the gap between simulator and reality. Previously, OpenAI used domain randomization to train a 5-finger robot hand to manipulate a Rubik's Cube: IEEE news article gave hints about the pipeline: Finally, praying for world peace 🙏. I hope robotics like this will bring more joy to the world.

Jim Fan

314,694 次观看 • 2 年前

Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:07 - Is robot locomotion solved? 06:04 - Sim-to-real gap 08:58 - Adding semantics to policies 09:42 - Modular vs end-to-end architectures 10:29 - Planner model 12:21 - Adapting RL techniques from quadrupeds to humanoids 15:39 - Behind robot demos 18:09 - Humanoid robots in home environments 22:03 - Training approach 23:56 - VLA models 27:59 - Closing the sim-to-real gap 32:55 - Task orchestration using VLMs 36:38 - Tool use 38:10 - Model hierarchy 43:37 - Simulator versus simulation environment 44:57 - Combining imitation learning and reinforcement learning 46:42 - RL in real world versus RL in simulation 52:58 - Reward tuning and value functions in robotics 56:38 - Predictions 1:00:10 - Humanoids, quadropeds, and wheeled platforms 1:02:45 - Advice, recommended robot kits, and community pla

Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:07 - Is robot locomotion solved? 06:04 - Sim-to-real gap 08:58 - Adding semantics to policies 09:42 - Modular vs end-to-end architectures 10:29 - Planner model 12:21 - Adapting RL techniques from quadrupeds to humanoids 15:39 - Behind robot demos 18:09 - Humanoid robots in home environments 22:03 - Training approach 23:56 - VLA models 27:59 - Closing the sim-to-real gap 32:55 - Task orchestration using VLMs 36:38 - Tool use 38:10 - Model hierarchy 43:37 - Simulator versus simulation environment 44:57 - Combining imitation learning and reinforcement learning 46:42 - RL in real world versus RL in simulation 52:58 - Reward tuning and value functions in robotics 56:38 - Predictions 1:00:10 - Humanoids, quadropeds, and wheeled platforms 1:02:45 - Advice, recommended robot kits, and community pla

The TWIML AI Podcast

22,592 次观看 • 7 个月前

Reinforcement Learning from Human Feedback (RLHF) is gaining traction. This field aims to make AI more responsible by including human values and preferences. In this video, Nathan Lambert, a research scientist and RLHF team lead at Hugging Face explores its inner workings, applications and industry impact. RLHF has gained the spotlight in recent years. The growth of language models like Anthropic’s Claude and OpenAI's ChatGPT have increased interest in human-feedback integration. "There are some rumors that Open AI had two teams; one was doing RLHF and the other instruction fine-tuning. And the RLHF team kept getting more and more performance." Understanding RLHF The RLHF process has three main steps: Pre-training: Much like with GPT models, the journey starts with pre-training on a large corpus of data. This can range from text data, web scrapes, to specialized datasets. Reward Modeling: This is the RLHF counterpart of supervised fine-tuning in large language models. This stage involves creating a reward model that resonates with human values and preferences. RL Optimization: This stage parallels reward modeling and reinforcement learning in traditional AI models. The AI system fine-tunes itself based on the reward model, employing reinforcement learning algorithms for that extra layer of optimization. The Data Challenge Data collection and curation in RLHF closely resemble the challenges you'd encounter in large language model training. Datasets from organizations like OpenAI can serve as a useful foundation. However, the need for high-quality, task-specific data cannot be overstated. Implementing RLHF: A Practical Guide If you’re someone who loves getting hands-on with AI libraries like Hugging Face, implementing RLHF is right way to do. It’s essential to understand its limitations. Think about model stability, over-optimization, and exploration strategies, much like you would when prompt engineering. Ongoing Research and Next Steps While he suggests that some basics figured out, there are layers of complexity that still need to be unraveled: 1. New Benchmarks: How do we measure the effectiveness of RLHF? 2. Preference Modeling: How can the model be made to understand human preferences better? 3. Interpreting RLHF: Much like explainability in traditional models, how do we make RLHF more interpretable? 4. System-Wide Evaluation: Going beyond individual performance, how does RLHF affect an entire system? The Transformative Power of RLHF Whether you're an AI developer, a business analyst, or a marketer, RLHF promises to revolutionize your domain. Imagine customer service chatbots that understand human emotions better, or content generators that align more closely with human values. RLHF is an emerging field that focuses on enhancing machine learning models through human feedback. While it tackles important issues like bias and ethics, its broader goal is to improve system performance across various applications. Whether you're deeply invested in the ethics of AI or simply curious about advancements in machine learning, RLHF offers valuable insights. If you're interested in the next wave of AI development, this area is definitely one to watch.

Reinforcement Learning from Human Feedback (RLHF) is gaining traction. This field aims to make AI more responsible by including human values and preferences. In this video, Nathan Lambert, a research scientist and RLHF team lead at Hugging Face explores its inner workings, applications and industry impact. RLHF has gained the spotlight in recent years. The growth of language models like Anthropic’s Claude and OpenAI's ChatGPT have increased interest in human-feedback integration. "There are some rumors that Open AI had two teams; one was doing RLHF and the other instruction fine-tuning. And the RLHF team kept getting more and more performance." Understanding RLHF The RLHF process has three main steps: Pre-training: Much like with GPT models, the journey starts with pre-training on a large corpus of data. This can range from text data, web scrapes, to specialized datasets. Reward Modeling: This is the RLHF counterpart of supervised fine-tuning in large language models. This stage involves creating a reward model that resonates with human values and preferences. RL Optimization: This stage parallels reward modeling and reinforcement learning in traditional AI models. The AI system fine-tunes itself based on the reward model, employing reinforcement learning algorithms for that extra layer of optimization. The Data Challenge Data collection and curation in RLHF closely resemble the challenges you'd encounter in large language model training. Datasets from organizations like OpenAI can serve as a useful foundation. However, the need for high-quality, task-specific data cannot be overstated. Implementing RLHF: A Practical Guide If you’re someone who loves getting hands-on with AI libraries like Hugging Face, implementing RLHF is right way to do. It’s essential to understand its limitations. Think about model stability, over-optimization, and exploration strategies, much like you would when prompt engineering. Ongoing Research and Next Steps While he suggests that some basics figured out, there are layers of complexity that still need to be unraveled: 1. New Benchmarks: How do we measure the effectiveness of RLHF? 2. Preference Modeling: How can the model be made to understand human preferences better? 3. Interpreting RLHF: Much like explainability in traditional models, how do we make RLHF more interpretable? 4. System-Wide Evaluation: Going beyond individual performance, how does RLHF affect an entire system? The Transformative Power of RLHF Whether you're an AI developer, a business analyst, or a marketer, RLHF promises to revolutionize your domain. Imagine customer service chatbots that understand human emotions better, or content generators that align more closely with human values. RLHF is an emerging field that focuses on enhancing machine learning models through human feedback. While it tackles important issues like bias and ethics, its broader goal is to improve system performance across various applications. Whether you're deeply invested in the ethics of AI or simply curious about advancements in machine learning, RLHF offers valuable insights. If you're interested in the next wave of AI development, this area is definitely one to watch.

Muratcan Koylan

27,168 次观看 • 2 年前

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 次观看 • 8 个月前

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

Chris Paxton

20,486 次观看 • 1 年前

New short course on Reinforcement Learning from Human Feedback! RLHF is one of the key techniques that led to the rise of modern LLMs. It is used to align LLMs with human preferences, to make them more honest, helpful and harmless, by (i) learning a reward function that mimics human preferences, as expressed in human-provided labels, then, (ii) tuning an LLM to generate outputs that receive a high reward. In this course, taught by Nikita Namjoshi, Developer Advocate for GenAI at Google Cloud, you'll learn the details of how RLHF works, including how to apply it to tune an LLM for your own applications. You'll also use an open source library to tune a base LLM to align with human preferences expressed in a training set, and evaluate the tuned model by comparing its responses before and after RLHF-tuning. Please sign up here!

New short course on Reinforcement Learning from Human Feedback! RLHF is one of the key techniques that led to the rise of modern LLMs. It is used to align LLMs with human preferences, to make them more honest, helpful and harmless, by (i) learning a reward function that mimics human preferences, as expressed in human-provided labels, then, (ii) tuning an LLM to generate outputs that receive a high reward. In this course, taught by Nikita Namjoshi, Developer Advocate for GenAI at Google Cloud, you'll learn the details of how RLHF works, including how to apply it to tune an LLM for your own applications. You'll also use an open source library to tune a base LLM to align with human preferences expressed in a training set, and evaluate the tuned model by comparing its responses before and after RLHF-tuning. Please sign up here!

Andrew Ng

205,562 次观看 • 2 年前