Deep deterministic portfolio optimization
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2020-11-01
|
| Series: | Journal of Finance and Data Science |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405918820300118 |
| _version_ | 1797203169308049408 |
|---|---|
| author | Ayman Chaouki Stephen Hardiman Christian Schmidt Emmanuel Sérié Joachim de Lataillade |
| author_facet | Ayman Chaouki Stephen Hardiman Christian Schmidt Emmanuel Sérié Joachim de Lataillade |
| author_sort | Ayman Chaouki |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-24T08:15:03Z |
| format | Article |
| id | doaj.art-81017f6f729046e6ad4ff5876a37b0ec |
| institution | Directory Open Access Journal |
| issn | 2405-9188 |
| language | English |
| last_indexed | 2024-04-24T08:15:03Z |
| publishDate | 2020-11-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Finance and Data Science |
| spelling | doaj.art-81017f6f729046e6ad4ff5876a37b0ec2024-04-17T04:08:46ZengKeAi Communications Co., Ltd.Journal of Finance and Data Science2405-91882020-11-0161630Deep deterministic portfolio optimizationAyman Chaouki0Stephen Hardiman1Christian Schmidt2Emmanuel Sérié3Joachim de Lataillade4Capital Fund Management, 23 rue de l'Université, 75007, Paris, France; École Centrale-Suplec, Gif-Sur-Yvette, FranceCapital Fund Management, 23 rue de l'Université, 75007, Paris, FranceCapital Fund Management, 23 rue de l'Université, 75007, Paris, France; Chair of Econophysics and Complex Systems, École Polytechnique, Palaiseau, FranceCapital Fund Management, 23 rue de l'Université, 75007, Paris, France; Corresponding author.Capital Fund Management, 23 rue de l'Université, 75007, Paris, FranceCan 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.http://www.sciencedirect.com/science/article/pii/S2405918820300118Reinforcement learningStochastic controlPortfolio optimization |
| spellingShingle | Ayman Chaouki Stephen Hardiman Christian Schmidt Emmanuel Sérié Joachim de Lataillade Deep deterministic portfolio optimization Journal of Finance and Data Science Reinforcement learning Stochastic control Portfolio optimization |
| title | Deep deterministic portfolio optimization |
| title_full | Deep deterministic portfolio optimization |
| title_fullStr | Deep deterministic portfolio optimization |
| title_full_unstemmed | Deep deterministic portfolio optimization |
| title_short | Deep deterministic portfolio optimization |
| title_sort | deep deterministic portfolio optimization |
| topic | Reinforcement learning Stochastic control Portfolio optimization |
| url | http://www.sciencedirect.com/science/article/pii/S2405918820300118 |
| work_keys_str_mv | AT aymanchaouki deepdeterministicportfoliooptimization AT stephenhardiman deepdeterministicportfoliooptimization AT christianschmidt deepdeterministicportfoliooptimization AT emmanuelserie deepdeterministicportfoliooptimization AT joachimdelataillade deepdeterministicportfoliooptimization |