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.

Deployment-Ready RL: Pitfalls, Lessons, and Best Practices We’ve published a full transcript of a webinar with Kyle🤖🚀🦭 (UT Austin) and the Humanoid team on our blog. He explores Sim2Real RL: - Action Space - Observation Space - Dealing with Model Mismatch - Reward Tuning Intuition - RL with Motion... show more

Humanoid

2,629 subscribers

60,003 views • 9 months ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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 🧵

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

130,935 views • 1 year ago

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition

Yitang Li

81,328 views • 7 months ago

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.

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

430,406 views • 3 months ago

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 views • 1 year ago

Sim2Real RL for Vision-Based Dexterous Manipulation on Humanoids TLDR - we train a humanoid robot with two multifingered hands to perform a range of dexterous manipulation tasks robust generalization and high performance without human demonstration :D

Sim2Real RL for Vision-Based Dexterous Manipulation on Humanoids TLDR - we train a humanoid robot with two multifingered hands to perform a range of dexterous manipulation tasks robust generalization and high performance without human demonstration :D

Toru

49,425 views • 1 year ago

Going to ICRA next week in Atlanta!! We are on a mission to build the most cracked team on humanoid robotics. Hiring the best talents on the research frontier of VLA, world models, RL, and simulation! DM or email me for meetup! linxif@nvidia.com

Going to ICRA next week in Atlanta!! We are on a mission to build the most cracked team on humanoid robotics. Hiring the best talents on the research frontier of VLA, world models, RL, and simulation! DM or email me for meetup! [email protected]

Jim Fan

130,549 views • 1 year ago

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Qiayuan Liao

80,294 views • 1 year ago

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)

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

1,051,007 views • 8 months ago

Autonomous drone racing demo with direct Pixel to Action and Deep RL. Robotics: Science and Systems

Autonomous drone racing demo with direct Pixel to Action and Deep RL. Robotics: Science and Systems

Yunlong Song

19,694 views • 1 year ago

My 10-week independent project for the Northwestern University MSR (MS in Robotics) program: Northwestern Humanoid. In short, I built the humanoid robot's hardware, integrated its motors and sensors with ROS, and successfully simulated its walking using an RL policy. #Robotics

My 10-week independent project for the Northwestern University MSR (MS in Robotics) program: Northwestern Humanoid. In short, I built the humanoid robot's hardware, integrated its motors and sensors with ROS, and successfully simulated its walking using an RL policy. #Robotics

Lele Burger

37,740 views • 1 year ago

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

The Humanoid Hub

20,051 views • 1 year ago

🤖 Introducing H2O (Human2HumanOid): - 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework - 💃 Scalable retargeting and training using large human motion dataset - 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform actions like pick and place, walking, kicking, boxing, etc - 💡Unleash the potential of humanoids with human cognitive skills and adaptability 🔗:

🤖 Introducing H2O (Human2HumanOid): - 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework - 💃 Scalable retargeting and training using large human motion dataset - 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform actions like pick and place, walking, kicking, boxing, etc - 💡Unleash the potential of humanoids with human cognitive skills and adaptability 🔗:

Tairan He

96,714 views • 2 years ago

🚨 Without Any Motion Priors, how to make humanoids do versatile parkour jumping🦘, clapping dance🤸, cliff traversal🧗, and box pick-and-move📦 with a unified RL framework? Introduce WoCoCo: 🧗 Whole-body humanoid Control with sequential Contacts 🎯Unified designs for minimal tuning across tasks 🤖Generalize to various high-DoF robots Website:

🚨 Without Any Motion Priors, how to make humanoids do versatile parkour jumping🦘, clapping dance🤸, cliff traversal🧗, and box pick-and-move📦 with a unified RL framework? Introduce WoCoCo: 🧗 Whole-body humanoid Control with sequential Contacts 🎯Unified designs for minimal tuning across tasks 🤖Generalize to various high-DoF robots Website:

Wenli Xiao

70,321 views • 2 years ago

What’s Up with 4NE-1’s Knees? How Neura Robotics Is Rethinking Humanoid Bot Design 🤖 ➡️Watch full video here: Listen on Spotify: NEURA Robotics Humanoid Botangelist

What’s Up with 4NE-1’s Knees? How Neura Robotics Is Rethinking Humanoid Bot Design 🤖 ➡️Watch full video here: Listen on Spotify: NEURA Robotics Humanoid Botangelist

Marwa ElDiwiny

19,001 views • 1 year ago

In-hand cylinder rotation with RL. IROS 2025 Different sizes, zero-shot sim-to-real, and full dynamic tactile feedback — all in one hand. #Sharpa #SharpaWave #IROS2025 #Robotics #DexterousHand #Humanoid #TactileSensing #ReinforcementLearning #IssacSim

In-hand cylinder rotation with RL. IROS 2025 Different sizes, zero-shot sim-to-real, and full dynamic tactile feedback — all in one hand. #Sharpa #SharpaWave #IROS2025 #Robotics #DexterousHand #Humanoid #TactileSensing #ReinforcementLearning #IssacSim

Sharpa

112,434 views • 8 months ago

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9

Zhen Wu

810,675 views • 8 months ago

Our work, "A Primer on SO(3) Action Representations in Deep Reinforcement Learning," was accepted to #ICLR2026! We provide a systematic study of action representation choices in RL, showing that they fundamentally impact training stability and performance. #Robotics #AI #RL

Our work, "A Primer on SO(3) Action Representations in Deep Reinforcement Learning," was accepted to #ICLR2026! We provide a systematic study of action representation choices in RL, showing that they fundamentally impact training stability and performance. #Robotics #AI #RL

Learning Systems and Robotics Lab (is hiring!)

49,655 views • 3 months ago

AGIBOT has launched a cloud platform that lets users upload raw videos of dance, martial arts or gestures. It captures the motion, trains an RL policy for the X2 humanoid. It also includes tools to sync voiceovers and facial expressions with choreography.

AGIBOT has launched a cloud platform that lets users upload raw videos of dance, martial arts or gestures. It captures the motion, trains an RL policy for the X2 humanoid. It also includes tools to sync voiceovers and facial expressions with choreography.

The Humanoid Hub

32,733 views • 8 months ago

This is . . . how to build a humanoid. We went to Foundation Robotics and hung with Sankaet and shot the process of making a humanoid in stunning detail. Full episode right here -

This is . . . how to build a humanoid. We went to Foundation Robotics and hung with Sankaet and shot the process of making a humanoid in stunning detail. Full episode right here -

Ashlee Vance

14,484 views • 4 months ago