Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot

ArXi:2605.01096v1 Announce Type: new Reinforcement Learning (RL) has the potential to enable robots with fast, nonlinear, and unstable dynamics to reach the limits of their performance. However, most recent advances rely on carefully designed physics-based simulators and domain randomization to achieve successful sim-to-real transfer within reasonable wall-clock time.