Stock market prediction using DQN with DQNReg loss function

Title

Stock market prediction using DQN with DQNReg loss function

Creator

Sebastian A.; Habis K.V.; Shukla S.

Description

There have been many developments in predicting stock market prices using reinforcement learning. Recently, Google released a paper that designed a new loss function, specifically for meta-learning reinforcement learning. In this paper, implementation is done using this loss function to the reinforcement learning model, whose objective is to predict the stock price based on certain parameters. The reinforcement learning used is an encoderdecoder framework that is useful for extracting features from long sequence prices. The DQNReg loss function is implemented in the encoder-decoder model as it could provide strong adaptation performance in a variety of settings. The model can buy and sell the index, and the reward is the portfolio return after the days trading has concluded. To maximize yield the model must optimize reward function. The DQNReg loss implemented DQN network and the Huber loss DQN network is compared with the Sharpe ratio considered for return. 2024 selection and editorial matter, Arvind Dagur, Karan Singh, Pawan Singh Mehra & Dhirendra Kumar Shukla; individual chapters, the contributors.

Source

Artificial Intelligence, Blockchain, Computing and Security: Volume 1, Vol-1, pp. 58-63.

Date

2023-01-01

Publisher

CRC Press

Coverage

Sebastian A., Department of Computer Science Christ University, Bangalore, India; Habis K.V., Department of Computer Science Christ University, Bangalore, India; Shukla S., Department of Computer Science Christ University, Bangalore, India

Rights

Restricted Access

Relation

ISBN: 978-100384581-2; 978-103249393-0

Format

Online

Language

English

Type

Book chapter

Identifier

https://doi.org/10.1201/9781003393580-10

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85180055152&doi=10.1201%2f9781003393580-10&partnerID=40&md5=0f0e68e7264bd2cbb13cf0140e743dd3