🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

another reproduction! who will be the first to try and solve a harder task 👀

simulation is the way, thank you for having me on!

I won’t be at #ICML2025 but Adria will! He will be presenting the work he did during his time at my lab tomorrow from 11:00AM to 1:30PM, stop by and check it out!

for robotics it’s also way harder in general vs text. You have way more modalities of inputs, and sometimes robotics data labels not only includes language, but an entire trajectory (generated via teleop for example). it’s quite easy to teleop in a way that’s hard to learn from

very well written post on motion imitation

XLeRobot 0.2.3 (XLeVR) out! xlerobot.readthedocs.io • VR (Quest 3) Whole-body Control • Reads everything: head and hand poses, joysticks, and all the buttons • Minimal dependencies, web-based • Modular, can use it on other robots • Open-source, easy install, play in 20min

Probably the first and only public video from Skild AI: seeing Frankas, UR5s, humanoid arms - all bimanual robotiq 2f85 grippers?

It is a major policy failure that the US cannot accommodate top AI conferences due to visa issues.

more visual sim2real reproduction! This time with modifications to the original code

🔥🚨 Preprint alert: Relative Entropy Pathwise Policy Optimization #REPPO 🚨🔥 What if you could have on-policy training without the instability and parameter tuning that plagues #PPO? What if training with deterministic policy gradient just worked? With our new method it does!

might be the first time I made it personally on the trending developers list on github! One of the contributing factors being the lerobot sim2real code

this is a common bar for physical AGI and an incredibly difficult one But I generally hope more people target physical “ASI” since we want robots to be able to do tasks much faster/safer than humans

we need to move on to focusing on wall time more often. Fast dev cycles are what drive research and engineering to eventually being used by the broader public. Think of the success of isaac gym, that enabled fast iteration on locomotion and now everyone uses a variant of it. and

🤖 Train in Sim. Deploy in Reality. In 1 Hour. Excited to share this community project: #XLeRobot lerobot-#sim2real, trained a policy in #ManiSkill (PPO, only RGB input) on RTX 4090 — and deployed directly to a real #robot manipulator, no fine-tuning needed! 🎯 Pick task

collective punishment makes no sense especially during the middle of a race towards agi against other countries