Dactyl

Dactyl uses machine learning to train a robot Shadow Hand from scratch, using the same reinforcement learning algorithm code that OpenAI Five uses.

Dactyl, is trained entirely in simulation and transfers its knowledge to reality, adapting to real-world physics using techniques we’ve been working on for the past year. Dactyl learns from scratch using the same general-purpose reinforcement learning algorithm and code as OpenAI Five.

Dactyl is a system for manipulating objects using a Shadow Dexterous Hand. We place an object such as a block or a prism in the palm of the hand and ask Dactyl to reposition it into a different orientation; for example, rotating the block to put a new face on top. The network observes only the coordinates of the fingertips and the images from three regular RGB cameras.

Dactyl robot hand with a colored block resting on the palm