active-inference-robotics

SKILL.md

"The agent's job is to predict its actions by predicting its sensations." — Patrick Kenny

Second-order skill synthesizing Patrick Kenny's discrete active inference framework with K-Scale's JAX/MuJoCo robotics stack. This skill emerges from the constructive collision between:

| Hidden Markov Model | PhysicsEngine (MJX/MuJoCo) | | Observation distribution | Observation.observe(state) | | State inference Q(s) | Critic.forward(obs, carry) | | Action inference Q(a) | Actor.forward(obs, carry) | | Mean field factorization | Independent Q(st) per timestep | | Predictive distribution | Policy rollout trajectory |

Second-order skill synthesizing Patrick Kenny's discrete active inference framework with K-Scale's JAX/MuJoCo robotics stack for predictive coding in robot locomotion Source: plurigrid/asi.

View raw