Sam Austin AI·5d agoBest GitHub Repos for Offline RL and Imitation LearningYou have a pile of logged decisions: dispatcher choices, driver demonstrations, thermostat settings, or robot teleoperation runs. You can’t…
Aakash Agrawal·Oct 20Gurukul: Teaching a Robot Arm by Imitation, from ScratchPart 1: data, training, and an honest evaluation of an ACT policy, 10 out of 20 on a real SO-101 arm
Singhshivam·Oct 19Teaching an SO101 to sort blue candiesReal demonstrations, ACT, SmolVLA and an Isaac Lab experiment at B1S Hacktober Physical AI 2026
Arun Murugesan·Sep 28I Taught a ₹1000 Robot Arm to Pick and Place Objects Using SmolVLA 🤖How a hobby-servo arm, an Arduino Uno, and a fine-tuned vision-language-action model ended up doing real imitation learning on a budget…
Deepak Vij·Sep 25Scaling Robot Data with Simulation: Breaking Embodied AI’s Data BottleneckLanguage models learned from the internet. Robots have no internet to learn from. Simulation may be how we build one.
NYU Center for Data Science·Sep 18To Imitate a Crowd, a Model Has to Watch the Whole Crowd: Learning Under Common ShockWhen a political figure posts something market-moving, every trader feels it in the same instant, and the models researchers use to imitate…
Chunpak·Sep 16How I chose an imitation-learning arm after writing about Vision-Language-ActionIn my last piece, I tried to explain Vision-Language-Action。 That article stayed in the clouds on purpose. This one comes down to the desk.
AgileX Robotics·Aug 27What Is Mobile ALOHA? A Low-Cost Approach to Real-World Data Collection for Imitation LearningThis article looks at what Mobile ALOHA is, how it collects real-world data, and how it's reshaping embodied AI research and robot learning.
Sreejith Balakrishnan·Jul 28π₀, decoded — Part 1: The Problem, and Why the Answer Has to Be a DistributionWhy a robot policy cannot be a plain regressor — the MDP framing, the vision-language backbone, and the multimodality argument.
曾裕翔 Vincent Tseng·Jul 1[Isaac Sim]基於 BC-RNN-GMM 模仿學習之 Franka 機械手臂方塊分類教學（四）：訓練結果與驗證訓練 Loss 變好，執行成功率就會變高嗎？透過 TensorBoard 查看訓練結果，並以 Isaac Lab rollout 驗證成功率。A response icon2A response icon2
![[Isaac Sim]基於 BC-RNN-GMM 模仿學習之 Franka 機械手臂方塊分類教學（四）：訓練結果與驗證](https://miro.medium.com/v2/resize:fill:160:106/1*JXeb5Vr1fujn62PaiC9SVQ.png)
![[Isaac Sim]基於 BC-RNN-GMM 模仿學習之 Franka 機械手臂方塊分類教學（四）：訓練結果與驗證](https://miro.medium.com/v2/resize:fill:320:214/1*JXeb5Vr1fujn62PaiC9SVQ.png)