Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🤖Adding new RL algorithms to LeRobot just got much easier. Demo: HIL-SERL training with a SAC-based RL algorithm on an SO-100 for a hole-in-hand peg-in-hole task. Sparse reward, only 30 offline demos mixed with live robot experience, and ~1 hour of online training with human interventions only when the...

LeRobotHF's profile picture

LeRobot

17,462 subscribers

30,265 görüntüleme • 1 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-source code to run your own humanoid RL experiments in no time! Thread below 🧵
0:25

Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-source code to run your own humanoid RL experiments in no time! Thread below 🧵

Younggyo Seo

130,994 görüntüleme • 1 yıl önce

So you’ve trained your favorite diffusion/flow based policy, but it’s just not good enough 0-shot. Worry not, in our new work DSRL - we show how to *steer* pre-trained diffusion policies with off-policy RL, improving behavior efficiently enough for direct training in the real world! DSRL retains nice exploration from the base policy, but allows for quick improvement beyond this base policy with RL. The method is frustratingly simple, and super easy to throw on top of your favorite pretrained policy (VLA/diffusion policy, etc). Let’s think about how it works, 🧵 (1/10)
2:53

So you’ve trained your favorite diffusion/flow based policy, but it’s just not good enough 0-shot. Worry not, in our new work DSRL - we show how to *steer* pre-trained diffusion policies with off-policy RL, improving behavior efficiently enough for direct training in the real world! DSRL retains nice exploration from the base policy, but allows for quick improvement beyond this base policy with RL. The method is frustratingly simple, and super easy to throw on top of your favorite pretrained policy (VLA/diffusion policy, etc). Let’s think about how it works, 🧵 (1/10)

Abhishek Gupta

19,035 görüntüleme • 1 yıl önce

We asked Sholto Douglas from Anthropic about the costs of RL (Reinforcement Learning) runs. "In Dario Amodei's essay, he said that RL runs cost only $1M back in December." "RL is a more naively parallelizable and scalable than pre-training." "With pre-training, you need everything in one big data center ideally. For RL, in theory, you could scale all over the world."
0:37

We asked Sholto Douglas from Anthropic about the costs of RL (Reinforcement Learning) runs. "In Dario Amodei's essay, he said that RL runs cost only $1M back in December." "RL is a more naively parallelizable and scalable than pre-training." "With pre-training, you need everything in one big data center ideally. For RL, in theory, you could scale all over the world."

TBPN

76,634 görüntüleme • 1 yıl önce

We Luis Felipe Casas have successfully deployed an in-hand manipulation policy to the LEAP hand following RL training in MuJoCo Playground. Sim-to-real isn’t as straightforward as it seems. Policy design and real-world tuning matter. Working on improving the policy further.
0:49

We Luis Felipe Casas have successfully deployed an in-hand manipulation policy to the LEAP hand following RL training in MuJoCo Playground. Sim-to-real isn’t as straightforward as it seems. Policy design and real-world tuning matter. Working on improving the policy further.

Yu Xiang

11,053 görüntüleme • 3 ay önce

bro casually explains RL tuning for LLMs and the three critical components: training, inference, and environments. basically any RLVR algorithm such as GRPO comes down to this super simple concept.
1:42

bro casually explains RL tuning for LLMs and the three critical components: training, inference, and environments. basically any RLVR algorithm such as GRPO comes down to this super simple concept.

ℏεsam

102,344 görüntüleme • 5 ay önce

I've long wondered if we can make a humanoid robot do a 𝘄𝗮𝗹𝗹𝗳𝗹𝗶𝗽 - and we just made it happen by leveraging 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁 with BeyondMimic tracking! This came after our original OmniRetarget experiments, with only minor tweaks to RL training: relaxing a termination threshold and removing one reward term. The policy achieved a 𝟱/𝟱 success rate in our real-world experiments, showing the strength of high-quality, interaction-preserving motion retargeting combined with BeyondMimic’s minimal RL tracking. Here is the updated arXiv: (In Sec. V. A)
0:20

I've long wondered if we can make a humanoid robot do a 𝘄𝗮𝗹𝗹𝗳𝗹𝗶𝗽 - and we just made it happen by leveraging 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁 with BeyondMimic tracking! This came after our original OmniRetarget experiments, with only minor tweaks to RL training: relaxing a termination threshold and removing one reward term. The policy achieved a 𝟱/𝟱 success rate in our real-world experiments, showing the strength of high-quality, interaction-preserving motion retargeting combined with BeyondMimic’s minimal RL tracking. Here is the updated arXiv: (In Sec. V. A)

Zhen Wu

1,051,049 görüntüleme • 9 ay önce

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.
2:15

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

431,973 görüntüleme • 3 ay önce

Engineers at XPENG developed an RL pipeline to achieve a natural walking gait for the IRON humanoid, tailoring both the data and the algorithm to adapt to the stiffness of its lattice skin.
1:15

Engineers at XPENG developed an RL pipeline to achieve a natural walking gait for the IRON humanoid, tailoring both the data and the algorithm to adapt to the stiffness of its lattice skin.

The Humanoid Hub

13,827 görüntüleme • 5 ay önce

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:
2:52

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 görüntüleme • 1 yıl önce

If you have a policy that uses diffusion/flow (e.g. diffusion VLA), you can run RL where the actor chooses the noise, which is then denoised by the policy to produce an action. This method, which we call diffusion steering (DSRL), leads to a remarkably efficient RL method! 🧵👇
0:39

If you have a policy that uses diffusion/flow (e.g. diffusion VLA), you can run RL where the actor chooses the noise, which is then denoised by the policy to produce an action. This method, which we call diffusion steering (DSRL), leads to a remarkably efficient RL method! 🧵👇

Sergey Levine

152,824 görüntüleme • 1 yıl önce

Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. 1/n
1:24

Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. 1/n

Ananye Agarwal

64,403 görüntüleme • 1 yıl önce

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.
0:22

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.

Lerrel Pinto

46,221 görüntüleme • 1 yıl önce

Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a human-demonstration for a novel task during inference One-shot human imitation *without* requiring any paired human-robot data or online RL 🙂 1/n
0:30

Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a human-demonstration for a novel task during inference One-shot human imitation *without* requiring any paired human-robot data or online RL 🙂 1/n

Homanga Bharadhwaj

32,830 görüntüleme • 1 yıl önce

1/ Introducing RL Swarm’s new backend: GenRL. A modular reinforcement learning library built for distributed, fault-tolerant training - now powering RL Swarm from the ground up. 🧵
0:50

1/ Introducing RL Swarm’s new backend: GenRL. A modular reinforcement learning library built for distributed, fault-tolerant training - now powering RL Swarm from the ground up. 🧵

gensyn

82,174 görüntüleme • 1 yıl önce

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇
0:33

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

Ilia

20,155 görüntüleme • 13 gün önce

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!
0:35

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!

Avi Chawla

138,554 görüntüleme • 4 ay önce

We are moving from model controller to RL for locomotion. The policy is starting to look quite robust. Even more convinced now that legs are easier than wheels, given the software complexity has shrunk tremendously with RL.
0:26

We are moving from model controller to RL for locomotion. The policy is starting to look quite robust. Even more convinced now that legs are easier than wheels, given the software complexity has shrunk tremendously with RL.

Sankaet

133,130 görüntüleme • 9 ay önce

verifiers v0.1.7 is released 🚀 this one's all about making RL training and experimentation waaaay easier: - single-command installation for prime-rl - single-command training w/ unified configs - overhauled vf.RLTrainer for hacking on new algorithms quick demo + links below :)
10:16

verifiers v0.1.7 is released 🚀 this one's all about making RL training and experimentation waaaay easier: - single-command installation for prime-rl - single-command training w/ unified configs - overhauled vf.RLTrainer for hacking on new algorithms quick demo + links below :)

will brown

28,579 görüntüleme • 8 ay önce

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.
0:12

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

356,747 görüntüleme • 1 yıl önce