Jonatha AnselmiBruno GaujalLouis-Sébastien RebuffiReinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space.2023abs/2302.10667CoRRhttps://doi.org/10.48550/arXiv.2302.10667db/journals/corr/corr2302.html#abs-2302-10667