Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedback

Abstract

We present a minimal phase oscillator model for learning quadrupedal locomotion. Each of the four oscillators is coupled only to itself and its corresponding leg through local feedback of the ground reaction force, which we interpret as an observer feedback gain. The oscillator itself is interpreted as a latent contact state-estimator. Through a systematic ablation study, we show that the combination of phase observations, simple phase-based rewards, and the local feedback dynamics induces policies that exhibit emergent gait preferences, while using a reduced set of simple rewards, and without prescribing a specific gait.