act_train_improve_merge is an open-source model for robotics that implements imitation learning with action chunking. It allows researchers to train, evaluate, and improve robotic policies using teleoperated data, supporting integration with robotics libraries and local experimentation.
Act Train Improve Merge is an Other AI product. It enables robotics researchers to train and evaluate imitation learning policies using action chunking methods. It is built as an open-source project for robotics researchers and developers. Act Train Improve Merge is open source under the Apache-2.0 license. It runs on the web and the command line, and it can be self-hosted.
Behind Act Train Improve Merge is qilahyana, and the product first shipped in 2024. Development happens publicly on GitHub with 25.8k stars and 157 commits in the last 90 days. Key capabilities include imitation learning, action chunking, and policy evaluation.
Latest indexed changes and source events
qilahyana/act_train_improve_merge verified by the PulseGate indexer
Other apps tracked under the same category.
