act_policy is an imitation-learning model for robotics that predicts short action chunks instead of single steps, improving success rates in manipulation tasks. It is compatible with LeRobot and supports research in robotic learning from demonstration.
In the Other AI space, Act Policy takes a focused approach. It focuses on enabling efficient imitation learning for robotics by predicting short action chunks from teleoperated data. It is built as an open-source project for robotics researchers and AI developers. Act Policy is open source under the Open Source license. The product ships for the web, the command line, and API.
It is developed by nivwa12, and the product first shipped in 2023. Key capabilities include imitation learning, action chunking, and robotics policy.
Latest indexed changes and source events
nivwa12/act_policy verified by the PulseGate indexer
Other apps tracked under the same category.
