poster · SAB 2026

Latent Representations Encoding Behavior and Modulating Adaptivity in Locomotion Learning

Janosch Bajorath · Malte Schilling

Poster and extended material will appear here around the conference (19–22 October 2026).

Abstract

Current quadruped locomotion control approaches are based on deep reinforcement learning and impose certain forms of behavioral structure through gait priors, reward shaping, or imitation. Bottom-up methods relax these priors, but typically retain an auxiliary objective that steers the latent representation $z_t$ toward a chosen geometry. Our work focuses on locomotion learning from a latent-centric perspective: what behavioral organization emerges inside a controller when no such structure is forced onto the system in a top-down fashion, and no bottom-up auxiliary objective guides $z_t$ either. We analyze how locomotor coordination forms within $z_t$ and explore whether the evolution of $z_t$ can itself guide training toward greater behavioral adaptivity.