SOURCE-LINKED INTELLIGENCE

Mind the Phase: Effective Rank and Representation Health in Legged Locomotion

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Reinforcement learning has become the leading paradigm in legged locomotion, enabling complex behaviors from backflips to parkour through massively parallel simulation. Under PPO's non-stationarity, shallow networks remain the de facto architecture, supported by carefully staged curricula and environments, yet the representations these policies learn stay poorly understood, leaving no training-time signal of how they will behave on hardware. In this work, we empirically study locomotion policies through the effective rank of the policy Jacobian and show that conditioning rank on the gait phase

Read original source ↗ Open in workspace

recordType

paper

region

Global