Skip to main content
Search

University of Stirling

1 related articles

Subscribe to updates
  1. arXiv

    When reality outpaces cognition: Co4 holds reliable behavior ten times further on complex quadruped locomotion, twice as far in car racing

    Reinforcement-learning agents are usually trained at one rate of environmental change but deployed where reality moves faster. This proof of concept raises the Speed of Reality step by step without retraining, measures how far each system keeps a preset behavioral reliability criterion, and compares a Transformer, a gated MLP and Co4, an architecture inspired by cellular mechanisms. On complex vision-guided quadruped locomotion, Co4 extends the continuously reliable range tenfold over the Transformer baseline; on car racing it extends it twofold.

You’re all caught up