Active Inference Robotics

Bridge active inference theory with robot control using K-Scale's JAX/MuJoCo stack. Use when connecting predictive coding to locomotion policies, mapping KL divergence minimization to RL training, applying mean field approximation to robotics state estimation, or implementing sim2real as inference about future observations.

plurigrid Updated 72 repo stars

File contents

plurigrid/asi commit 14ceb61276

Frequently asked questions

npx get-skill add plurigrid/active-inference-robotics