Autor:	Chaouki, Ayman, Hardiman, Stephen, Schmidt, Christian, Sérié, Emmanuel, de Lataillade, Joachim
Rok vydání:	2020
Předmět:	Quantitative Finance - Mathematical Finance Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Can deep reinforcement learning algorithms be exploited as solvers for optimal trading strategies? The aim of this work is to test reinforcement learning algorithms on conceptually simple, but mathematically non-trivial, trading environments. The environments are chosen such that an optimal or close-to-optimal trading strategy is known. We study the deep deterministic policy gradient algorithm and show that such a reinforcement learning agent can successfully recover the essential features of the optimal trading strategies and achieve close-to-optimal rewards. Comment: Minor typo
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2003.06497 Zobrazit plný text záznamu View this record from Arxiv