Zombie robot RL policy

New project! Flow Policy Gradients for Robot Control tldr;... a simple online RL recipe for training and fine-tuning flow policies for robots co-led w/ Hongsuk Benjamin Choi:show more

Intense battle! A crucial opportunity for number 3! #bipedal... #Robot #RLshow more

Does LLM RL post-training need to be on-policy?

Pantograph robot building with jenga blocks. Focusing on RL... is a great and fairly unique strategyshow more

They pump air into dead spiders and make them... in to zombie robot end effectors…show more

Zombie o Zombieee ehe!

🚨Current scalable RL algos train a policy w/o value... func, which is limiting with learning in open-ended, non-stationary, dynamic environments. But, how to scale value-based RL with more data/compute is unclear... Not anymore: presenting scaling laws for value-based RL 🧵⬇️show more

🤔 How to fine-tune an Imitation Learning policy (e.g.,... Diffusion Policy, ACT) with RL? As an RL practitioner, I’ve been struggling with this problem for a while. Here’s why it’s tough: 1️⃣ Special designs (usually for multimodal action distributions) in modern IL models make them non-trivial to fine-tune by RL. 2️⃣ Large policy models + RL's poor sample efficiency = a nightmare But finally, we figured out a simple solution that works for any model architecture! 🌟 Check out our #ICLR2025 paper: “Policy Decorator: Model-Agnostic Online Refinement for Large Policy Models”, led by my amazing mentee Xiu Yuan. 🔗 🧵 Read more below!show more

Benchmarking robot policies is broken We ran thousands of... evaluations over 12 different manipulation tasks to evaluate which robot policy you should use.show more

Thanks AK! Finally, robot can do continuous, agile, autonomous,... adaptive jumping over stair and stepping stone Key idea: combine the pros of model-free RL and model-based control. RL (for CoM refs) + QP (for GRF) + WBC (for torque) Open-sourced:show more

New research from Databricks: LLMs Can Learn to Reason... via Off-Policy RL Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL) shows you don’t need strict on-policy training to improve reasoning. It matches or beats Group Relative Policy Optimization (GRPO), stays stable with large policy lag, and uses ~3× fewer training generations. For Databricks customers, it’s a simpler, practical, and equally powerful approach to RL that Databricks is pioneering internally — and bringing directly to Databricks customers, so enterprises can improve agents using the same methods we use for our in-house agents, without complex infrastructure changes.show more

Generalist robot policies need a benchmark that works across... any robot and any policy. 🦾 Introducing RoboLab, a high‑fidelity simulation benchmark built on NVIDIA Isaac and Omniverse to evaluate generalist robot policies in diverse, photoreal, physics‑based environments. Coming soon to the NVIDIA Isaac Lab‑Arena roadmap for large‑scale, robotic policy evaluation. 📖 #NationalRoboticsWeekshow more

I've gotten a mujoco sim RL training loop for... a unitree robot at 200k SPS. I'm looking into the physics for friction, contact dynamics. My goal: can I reproduce & beat the mujoco playground RL baselines This is running in my web browser with raylib. Its the baselineshow more

Creating a "unified" policy for a robot is uniquely... challenging for two reasons: (a) data is scarce; (b) a single robot can only act sequentially. In PolyTask, we learn a single policy to solve many tasks in a lifelong fashion given *just 1 demonstration* for each task. 🧵show more

Robot Edward Warchocki został zatrzymany 😭

Ten robot skradł dziś show 😅