act_task1_v2 is an open-source imitation learning policy for robotics, trained to predict action chunks from teleoperated data. It is designed for use with LeRobot and supports local inference and further training by robotics researchers and engineers.
Act Task1 sits in PulseGate's Other AI category. It focuses on enabling robotics researchers to use and train action chunking policies for imitation learning tasks. Act Task1 is an open-source project aimed at robotics researchers and engineers. The project is open source (Apache-2.0). It runs on the web, and it can be self-hosted.
leeohwang builds and maintains Act Task1, and the product first shipped in 2024. The project is developed in the open on GitHub with 25.7k stars and 164 commits in the last 90 days. Across PulseGate's embedding index, Act Task1 has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are imitation learning, robotics policy, and open weights.
Latest indexed changes and source events
leeohwang/act_task1_v2 discovered by the PulseGate indexer
