NatureDiscovering state-of-the-art reinforcement learning algorithmsJunhyuk OhGregory FarquharIurii KemaevDan A. CalianMatteo HesselLuisa ZintgrafSatinder SinghHado van HasseltDavid Silver2025-10-22Full textDOI https://doi.org/10.1038/s41586-025-09761-x