Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning

Algorithmic trading allows investors to avoid emotional and irrational trading decisions and helps them make profits using modern computer technology. In recent years, reinforcement learning has yielded promising results for algorithmic trading. Two prominent challenges in algorithmic trading with r...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Deog-Yeong Park, Ki-Hoon Lee
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Algorithmic trading deep learning state representation learning imitation learning reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/fec1d81fddfe4844bbcbdf81d0705b41
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fec1d81fddfe4844bbcbdf81d0705b41
record_format	dspace
spelling	oai:doaj.org-article:fec1d81fddfe4844bbcbdf81d0705b412021-11-20T00:01:02ZPractical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning2169-353610.1109/ACCESS.2021.3127209https://doaj.org/article/fec1d81fddfe4844bbcbdf81d0705b412021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9611246/https://doaj.org/toc/2169-3536Algorithmic trading allows investors to avoid emotional and irrational trading decisions and helps them make profits using modern computer technology. In recent years, reinforcement learning has yielded promising results for algorithmic trading. Two prominent challenges in algorithmic trading with reinforcement learning are (1) extracting robust features and (2) learning a profitable trading policy. Another challenge is that it was previously often assumed that both long and short positions are always possible in stock trading; however, taking a short position is risky or sometimes impossible in practice. We propose a practical algorithmic trading method, <italic>SIRL-Trader</italic>, which achieves good profit using only long positions. SIRL-Trader uses offline/online state representation learning (SRL) and imitative reinforcement learning. In offline SRL, we apply dimensionality reduction and clustering to extract robust features whereas, in online SRL, we co-train a regression model with a reinforcement learning model to provide accurate state information for decision-making. In imitative reinforcement learning, we incorporate a behavior cloning technique with the twin-delayed deep deterministic policy gradient (TD3) algorithm and apply multistep learning and dynamic delay to TD3. The experimental results show that SIRL-Trader yields higher profits and offers superior generalization ability compared with state-of-the-art methods.Deog-Yeong ParkKi-Hoon LeeIEEEarticleAlgorithmic tradingdeep learningstate representation learningimitation learningreinforcement learningElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152310-152321 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Algorithmic trading deep learning state representation learning imitation learning reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Algorithmic trading deep learning state representation learning imitation learning reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971 Deog-Yeong Park Ki-Hoon Lee Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning
description	Algorithmic trading allows investors to avoid emotional and irrational trading decisions and helps them make profits using modern computer technology. In recent years, reinforcement learning has yielded promising results for algorithmic trading. Two prominent challenges in algorithmic trading with reinforcement learning are (1) extracting robust features and (2) learning a profitable trading policy. Another challenge is that it was previously often assumed that both long and short positions are always possible in stock trading; however, taking a short position is risky or sometimes impossible in practice. We propose a practical algorithmic trading method, <italic>SIRL-Trader</italic>, which achieves good profit using only long positions. SIRL-Trader uses offline/online state representation learning (SRL) and imitative reinforcement learning. In offline SRL, we apply dimensionality reduction and clustering to extract robust features whereas, in online SRL, we co-train a regression model with a reinforcement learning model to provide accurate state information for decision-making. In imitative reinforcement learning, we incorporate a behavior cloning technique with the twin-delayed deep deterministic policy gradient (TD3) algorithm and apply multistep learning and dynamic delay to TD3. The experimental results show that SIRL-Trader yields higher profits and offers superior generalization ability compared with state-of-the-art methods.
format	article
author	Deog-Yeong Park Ki-Hoon Lee
author_facet	Deog-Yeong Park Ki-Hoon Lee
author_sort	Deog-Yeong Park
title	Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning
title_short	Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning
title_full	Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning
title_fullStr	Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning
title_full_unstemmed	Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning
title_sort	practical algorithmic trading using state representation learning and imitative reinforcement learning
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/fec1d81fddfe4844bbcbdf81d0705b41
work_keys_str_mv	AT deogyeongpark practicalalgorithmictradingusingstaterepresentationlearningandimitativereinforcementlearning AT kihoonlee practicalalgorithmictradingusingstaterepresentationlearningandimitativereinforcementlearning
_version_	1718419874831663104

Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning

Ejemplares similares