Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding Discrete-time Hybrid Automata Learning (DHAL) is a framework that uses on-policy Reinforcement Learning to identify and execute mode-switching without needing trajectory segmentation or event function learning. Hybrid dynamical systems, which combine continuous flow and discrete mode switching, are useful for modeling tasks like legged robot locomotion. Traditional model-based methods rely on predefined gaits, while mo