Jiang, RuihongSaunders, DavidWeng, Chengguo2023-11-072023-11-072022-03https://doi.org/10.1080/14697688.2022.2049356http://hdl.handle.net/10012/20094This is an Accepted Manuscript of an article published by Taylor & Francis in Quantitative Finance on 24 March 2022, available online: https://doi.org/10.1080/14697688.2022.2049356The full Kelly portfolio strategy's deficiency in the face of estimation errors in practice can be mitigated by fractional or shrinkage Kelly strategies. This paper provides an alternative, the RL Kelly strategy, based on a reinforcement learning (RL) framework. RL algorithms are developed for the practical implementation of the RL Kelly strategy. Extensive simulation studies are conducted, and the results confirm the superior performance of the RL Kelly strategies.enKelly criterionfractional Kelly strategyportfolio selectionreinforcement learningArticle