Task-Agnostic Morphology Evolution

tame_video.mp4

Evolving Morphologies without Rewards.

We propose a new algorithm, TAME, that is able to evolve morphologies without any task specification. This is accomplished using an information theoretic objective that efficiently ranks morphologies based on their ability to explore and control their environment.

Code

A public release of our code can be found at: https://github.com/jhejna/morphology-opt

More video results...

For even more agent depictions, see the video at the top of this page.