DAPG
DAPG research team
Demonstration-augmented policy-gradient learning for dexterous hand manipulation.
What you can explore
Explore the original demonstrations, pretrained policies and linked learning environments.
Before you use it
A historical research stack with separate mjrl and mj_envs dependencies. Reproduction requires compatible environment versions.
Original contributors
Aravind Rajeswaran, Vikash Kumar and collaborators
License / access: Apache-2.0 · check model, data and dependency terms separately
Keep exploring
Gymnasium Robotics
MuJoCo robotics environments with Gymnasium interfaces, including dexterous hand tasks.
robomimic
A framework for training and evaluating manipulation policies from demonstrations.
Editorial reference · checked 2026-09-22