Title
Multi-DQN: An ensemble of Deep Q-learning agents for stock market forecasting
Abstract
•A novel ensembling methodology of RL agents with different training experiences.•Validation of such ensemble in intraday stock market trading.•Different combinations of ensemble decisions in stock markets.•Validation in different markets and periods of trading.•A multi-resolution feature set, which captures data prices at multiple time frames.
Year
DOI
Venue
2021
10.1016/j.eswa.2020.113820
Expert Systems with Applications
Keywords
DocType
Volume
Reinforcement learning,TD-learning,Q-learning,Financial signal processing,Neural networks for finance,Trading
Journal
164
ISSN
Citations 
PageRank 
0957-4174
2
0.44
References 
Authors
0
5