So101-act-test is an open-source robotics model implementing action chunking with transformers for imitation learning. It predicts short action sequences from teleoperated data, supporting robotics research and development. Distributed via Hugging Face with open weights and documentation for integration.
So101 Act Test sits in PulseGate's Other AI category. It focuses on enabling robotics developers to implement imitation-learning policies that predict action chunks for robots. It is built as an open-source project for robotics researchers and developers. So101 Act Test is open source under the Apache-2.0 license. So101 Act Test is available on the web, API, and the command line.
It is developed by AaronL20, and the product first shipped in 2024. Development happens publicly on GitHub with 25.7k stars and 164 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — So101 Act Test occupies a relatively distinct niche. Key capabilities include imitation learning, action chunking, and robotics policy.
Latest indexed changes and source events
AaronL20/So101-act-test discovered by the PulseGate indexer
Other apps tracked under the same category.
