Deep Direct Reinforcement Learning for Financial Signal Representation and Trading
The DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index.
Abstract
Can we train the computer to beat experienced traders for financial assert trading? In this paper, we try to address this challenge by introducing a recurrent deep neural network (NN) for real-time financial signal representation and trading. Our model is inspired by two biological-related learning concepts of deep learning (DL) and reinforcement learning (RL). In the framework, the DL part automatically senses the dynamic market condition for informative feature learning. Then, the RL module interacts with deep representations and makes trading decisions to accumulate the ultimate rewards in an unknown environment. The learning system is implemented in a complex NN that exhibits both the deep and recurrent structures. Hence, we propose a task-aware backpropagation through time method to cope with the gradient vanishing issue in deep training. The robustness of the neural system is verified on both the stock and the commodity future markets under broad testing conditions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In machinelearning systems, humans shape and reshape algorithms through their daily actions and interactions (Deng, Bao, Kong, Ren, & Dai, 2017).”
From Artificial Intelligence and Management: The Automation–Augmentation Paradox (2021) · cites this paper as Deng, Bao, Kong, Ren, & Dai, 2017
Citations
Cites
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
(1999) · Cited by 12,812
(1995) · Cited by 10,558
A neural substrate of prediction and reward
Schultz, W., Dayan, P., & Montague, P. R. (1997) · Science · doi:10.1126/science.275.5306.1593 · Cited by 9,388
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“DL techniques have been witnessed in image categorization [26] and speech recognition [29].”
MethodLearning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542 · cited 1×
“When directly applying the BPTT, the gradient vanish on deep layers is not avoided in the fine-tuning step [41].”
MethodMarkov decision processes: Discrete stochastic dynamic programming
Hazeghi, K., & Puterman, M. L. (1995) · Journal of the American Statistical Association · doi:10.2307/2291177 · Cited by 8,037
Research works printed but not linked: 1
- prokhorov, 2001, Dynamical neural networks for control, A Field Guide to Dynamical Recurrent Networks
Cited by
Items 601–700 of 822
Ensemble Deep Reinforcement Learning for Financial Trading
Vishal, M., Ravi, V., & Lal, R. (2024) · Intelligent systems reference library · doi:10.1007/978-3-031-61037-0_9 · Cited by 1
Bi-Directional Knowledge Transfer For Continual Deep Reinforcement Learning in Financial Trading
Katsikas, D., Passalis, N., & Tefas, A. (2024) · Machine learning for signal processing ... · doi:10.1109/mlsp58920.2024.10734752 · Cited by 1
“One particular area of DL that has seen remarkable advancements is Deep Reinforcement Learning (DRL) [6] providing models that are trained on maximizing profits directly through their reward functions [7, 8], instead of approximating the task through handcrafted proxy problems.”
BackgroundTransforming Algorithmic Trading with AI: Achieving Competitive Market Edge
Vardhan, H., Sharma, N. P., Kumar, M., Singh, R. K., Mandal, R., & Siraj, I. (2024) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart63812.2024.10882194 · Cited by 1
“Nevertheless, AI algorithmic trading[10] enables financial trading to be made more democratic since it is based on the usage of significant the data and provides all traders with the tools needed to conduct quick, precise, and bias-free investment decisions.”
A hierarchical deep learning framework for pair trading with attention and graph networks
Xia, Y., Wang, T., Liew, S. C., & Zhang, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128496 · Cited by 2
Sharma, S. K., Latifi, S., & Kachroo, P. P. E. (2025) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac65507.2025.00055 · Cited by 1
Mid-Curve Recommendation System: a Stacking Approach Through Neural Networks
Koshiyama, A., Firoozye, N. B., & Treleaven, P. C. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489229 · Cited by 1
“) we can find a vast amount of research using statistical and machine learning methods [4], [6], [11], [15], [19], [29], [30].”
MethodA Derivatives Trading Recommendation System: the Mid-Curve Calendar Spread Case
Koshiyama, A., Firoozye, N. B., & Treleaven, P. C. (2018) · Intelligent systems in accounting, finance and management/Intelligent systems in accounting, finance & management · doi:10.1002/isaf.1445 · Cited by 2
Empirical analysis of Deep Learning Model for Financial Data Prediction
Dharmadhikari, S., & More, A. (2019) · Cited by 1
Sreekumar, A., Kalkur, P., & Moiz, M. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-6001-5_10 · Cited by 1
A reinforcement learning model based on reward correction for quantitative stock selection
Chen, H., Zhang, C., & Li, Y. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/768/7/072036 · Cited by 1
Designing an Automated Trading System Using Convolutional Neural Network
Yaftian, A. H., & Rastegar, M. A. (2020) · نشریه چشم انداز مدیریت مالی · doi:10.52547/jfmp.10.31.153 · Cited by 1
“Applied Mathematical Finance, 20(6), 512-547.”
EDM-DRL: Toward Stable Reinforcement Learning Through Ensembled Directed Mutation
Prince, M. H., McGehee, A. J., & Tauritz, D. R. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72699-7_18 · Cited by 1
Asset Allocation Based On Reinforcement Learning
Li, Y., Wu, J., & Chen, Y. (2020) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin45582.2020.9442214 · Cited by 1
“Training intelligent agents for automated financial asserts trading is a time-honored topic that has been widely discussed in the modern artificial intelligence and fin-tech is developing rapidly in the world[2].”
Background“MR Q-Learning” Algorithm for Efficient Hardware Implementations
Cardarilli, G. C., Nunzio, L. D., Fazzolari, R., Giardino, D., Natale, D., Re, M., & Spanò, S. (2021) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf53345.2021.9723147 · Cited by 1
“In the last years, Reinforcement Learning (RL) [1] was employed in different fields, such as robotics [2]–[4], Internet of Things (IoT) [5], power management [6], financial trading [7], and telecommunications [8], [9].”
MethodSentiment-Aware Distillation for Bitcoin Trend Forecasting Under Partial Observability
Panagiotatos, G., Passalis, N., Tsantekidis, A., & Tefas, A. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746593 · Cited by 1
A-EMS: An Adaptive Emergency Management System for Autonomous Agents in Unforeseen Situations
Maguire, G., Ketz, N., Pilly, P. K., & Mouret, J.-B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-15908-4_21 · Cited by 2
Research on the Application of Artificial Intelligence Platform in Quantitative Investment
Wen, S. (2023) · Advances in Computer and Communication · doi:10.26855/acc.2023.06.009 · Cited by 2
Adversarial Attacks on Deep Algorithmic Trading PoliciesPreprint
Faghan, Y., Piazza, N., Behzadan, V., & Fathi, A. (2020) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2010.11388 · Cited by 6
“With recent advances in Machine Learning (ML), particularly in Deep Learning and Deep Reinforcement Learning (DRL), such challenges are dramatically alleviated via numerous novel proposals and architectures that enable end-to-end approaches to algorithmic trading [2].”
BackgroundDirichlet Policies for Reinforced Factor PortfoliosPreprint
André, E., & Coqueret, G. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3726714 · Cited by 12
zhao, Z., Caö, H., & Li, Y. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4008760 · Cited by 1
A proposal to improve research in AI algorithm and data governancePreprint
Braga, J., Regateiro, F. S., Stiubiener, I., & Braga, J. C. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/sr7kt · Cited by 1
Modern Machine Learning Tools in Finance: A Critical PerspectivePreprint
Allen, F., Kacperczyk, M. T., & Karri, S. S. K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5439898 · Cited by 3
Reinforcement Learning for systematic market making strategies
Ragel, V. (2024) · doi:10.70675/264ba758z2d7fz451fza648zac6644d60220 · Cited by 1
A Novel Experience-Based Exploration Method for Q-Learning
Yang, B., Lu, H., Li, B.-G., Zhang, Z., & Zhang, W. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-2203-7_17
Transfer Learning Approach for Fast Convergence of Deep Q Networks in Game Pong
Shao, B., Jiang, X., & Li, Q. (2018) · International Journal of Computer Applications · doi:10.5120/ijca2018917925
Kang, M.-J., Ahn, J., & Lee, J.-H. (2018) · Journal of Korean institute of intelligent systems · doi:10.5391/jkiis.2018.28.5.487
A P2P Lending Agency Risk Evaluation Approach Based on RL
Lv, Y. J., Li, L., Wang, T., & Zhao, T. (2018) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis.2018.8691357
Proxy Functions for Approximate Reinforcement Learning
Alibekov, E., Kubalı́k, J., & Babuška, R. (2019) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2019.09.145
Artificial Intelligence Security—Analysis on Adversarial Attacks
易, 楷. (2019) · Computer Science and Application · doi:10.12677/csa.2019.912249
“引言 随着人工智能深度学习成为研究热点,其在医疗[1]、生物[2] [3],金融[4]、自动驾驶[5]各个领域 皆有所应用,并且取得丰硕的成果。深度学习不同于传统的基于特征提取的机器学习,不需要使用者 掌握太多的专业知识,只需调节好参数即可取得很好的效果。人工智能深度学习应用极其广泛,此时 对人工智能安全的需求也迫在眉睫。早在 2015 年 IanGoodfellow 提出了对抗攻击的概念,对于熊猫图 片只需增加一点扰动,在人类视觉中干扰图片与原图差别很小,几乎无法看出,但是人工智能深度学 习模型却会以 99.”
REST: Performance Improvement of a Black Box Model via RL-Based Spatial Transformation
Kim, J. M., Kim, H., Park, C., & Lee, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6786
Application of Deep Q-Network in Portfolio ManagementPreprint
Gao, Z., Gao, Y., Hu, Y. Y., Jiang, Z., & Su, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06365
“Therefore, many studies [24],[25] solve the problem by Reinforcement Learning without predicting future prices.”
BackgroundAutonomous multi-agent collaborative environment exploration
Luo, T. (2019) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/136784
Hierarchical Attention Network for Action SegmentationPreprint
Gammulle, H., Denman, S., Sridharan, S., & Fookes, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.03209
“In early literature on continuous action recognition, most works utilise hand-crafted features such as HOG, HOF, MBH, Trajectory or pose based features for the action segmentation task (Fernando et al., 2015; Rohrbach et al., 2012). Apart from these, human-object interactions have been considered in (de La Gorce et al…”
InfluentialTowards coordinated multi-agent exploration problem via segmentation and reinforcement learning
Chen, Z. (2019) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/137152
Decentralized Deep Reinforcement Learning for Network Level Traffic Signal ControlPreprint
Guo, J. L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03433 · Cited by 5
“Deep Q Learning (DQL) has been achieving impressive success in high challenging tasks, e.g., robotic control (Gu et al, 2016), natural language processing (Sharma & Kaushik, 2017), finance (Deng et al., 2017), healthcare (Ling et al., 2017) and etc.”
BackgroundOn the Computation of Optimized Trading Policies Using Deep Reinforcement Learning
Corona-Bermúdez, U., Menchaca-Méndez, R., & Menchaca-Méndez, R. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-62554-2_7
Continuous Deep Q-Learning with Simulator for Stabilization of Uncertain Discrete-Time SystemsPreprint
Ikemoto, J., & Ushio, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05640
How Much Does Stock Prediction Improve with Sentiment Analysis?
Monteiro, F. G., & Ferreira, D. R. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-66981-2_2
A General Framework of Optimal InvestmentPreprint
Ye, T., & Zhang, L. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3136708 · Cited by 2
Essays in finance and behavioral economics
Wang, S. (2020) · Iowa State University Digital Repository (Iowa State University) · doi:10.31274/etd-20210114-157
Deep reinforcement learning on a multi-asset environment for tradingPreprint
Hirsa, A., Osterrieder, J. R., Misheva, B. H., & Posth, J.-A. (2021) · arXiv (Cornell University) · doi:10.21256/zhaw-22850
Online Trading Models in the Forex Market Considering Transaction CostsPreprint
Ishikawa, K., & Nakata, K. (2021) · arXiv (Cornell University)
Suggestion of Strategy for the Automation of Stocks Based on Reinforcement Learning
Hwang, H., Kim, Y., & Lee, Y. H. (2021) · Journal of Korean Institute of Industrial Engineers · doi:10.7232/jkiie.2021.47.4.399
Tariff Stroll For Monetary Trading Using Deep Learning
Sangeetha, N., Jayalakshmi, S. L., Raman, D. R., Saravanan, D., & Usharani, S. (2021) · International Conference on System, Computation, Automation and Networking (ICSCAN) · doi:10.1109/icscan53069.2021.9526462
“Departmental learning models, such as [5], [20]-[23], such as the convolutions of neural networks and LSTM, are used to forecast market movement attributes in a supervised manner directly.”
MethodRobust Deep Reinforcement Learning for Portfolio Management
Masoudi, M. (2021) · uO Research (University of Ottawa) · doi:10.20381/ruor-26960 · Cited by 2
Computational Recovery of Information From Low-quality and Missing Labels
Bao, F. (2021) · Springer theses · doi:10.1007/978-981-16-3064-4_3
Self-citationComputational Recovery of Sample Missings
Bao, F. (2021) · Springer theses · doi:10.1007/978-981-16-3064-4_4
Self-citationReinforcement Learning for Options on Target Volatility FundsPreprint
Daluiso, R., Nastasi, E., Pallavicini, A., & Polo, S. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3976899
“Because of its nature, RL has been successful in quantitative finance for solving control problems; among the most important RL applications in this field, we refer to Deng et al. (2017) as the pioneers in studying self-taught reinforcement trading problems, while to Kolm and Ritter (2019) and Halperin (2020) for hedg…”
MethodInfluentialSyntactic Analysis of Sentences Using Deep Neural Networks
Muñoz-Valero, D., Rodríguez-Benítez, L., Jiménez, L., & Moreno‐García, J. (2022) · Studies in computational intelligence · doi:10.1007/978-3-030-88817-6_5
Learning To Play The Trading Game
Kulkarni, N. (2019) · San José State University ScholarWorks (San Jose State University) · doi:10.31979/etd.cbe6-973x
Rubim, F. H. (2019) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.12.2019.tde-17032020-183245
Naqvi, A. (2021) · doi:10.1002/9781119601838.ch8
Júnior, C. O. V. (2020) · doi:10.31414/ee.2020.t.131152 · Cited by 1
Tools for automated reconstruction of neural circuits from optical microscopy images
Wang, S.-L. (2019) · Digital Repository Service (Northeastern University) · doi:10.17760/d20321282
On CVaR-Based Reinforcement Learning in Quantitative InvestmentPreprint
Alameer, A., & Alshehri, K. A. (2022) · doi:10.36227/techrxiv.19961525
32nd International Conference on Information Modelling and Knowledge Bases
(2022) · Kiel computer science series · doi:10.21941/kcss/2022/3
Strategic Earning on Tokenized Platforms via Model-based Decision MakingPreprint
Li, T. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4101301
Multi-Relational Graph Convolution Network Prediction of Climate Change Impact on FirmsPreprint
Gupta, A., Kar, K., Liu, S., Palepu, S. R. K. M. S., Popa, L., & Zhu, Y. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4140442
Uma proposta para impulsionar as pesquisas em governança de algoritmos de IA e dadosPreprint
Braga, J., Regateiro, F. S., Stiubiener, I., & Braga, J. C. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/xcpsd · Cited by 1
Chiumera, D. (2022) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2022-15153 · Cited by 5
“However with that in mind, it should be noted that this work also did not compare to a buy and hold strategy [53, 13].”
ResultMetelli, A. M. (2022) · Intelligenza Artificiale · doi:10.3233/ia-220140
“Remarkable successes have been achieved in industrial robot control [10], trading [7], playing videogames [30], and autonomous driving [14].”
An Optical Satellite Controller Based on Diffractive Deep Neural Network
Liu, S., Dou, H., Li, H., & Deng, Y. C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20500-2_4
Self-citationDeep Reinforcement Learning for Tehran Stock Trading
Yousefi, N. (2022) · Indonesian Journal of Data and Science · doi:10.56705/ijodas.v3i3.53
Adversarial Example Generation Method Based on Sensitive Features
Wen, Z., Shen, Z., Sun, H., & Qi, B. (2023) · Wuhan University Journal of Natural Sciences · doi:10.1051/wujns/2023281035
“Neural networks are now widely used in a variety of fields, including automatic driving [1,2] , medical treat‐ ment [3,4] , biology [5,6] , and finance [7] , where they have pro‐ duced remarkable results.”
BackgroundA Novel BNN-based Probabilistic Prediction Model for Non-linear and Non-stationary Time Series
Feng, K., Chen, P., Gan, Z., & Liu, L. (2022) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1145/3584376.3584509
“Jeong et al. proposed that Deep Q-Learning is used together with the DNN method and a 200-day stock price data set to predict the S&P 500 index [12].”
MethodOtimização de portfólio: uma análise através de técnicas de Reinforcement Learning e Autoencoders
de Melo, F. D. (2022) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.100.2022.tde-25112022-170424
Trần, T. K. T., Võ, M. H., Lê, L. N. T., & Vo, V. T. X. H. (2023) · Can Tho University Journal of Science · doi:10.22144/ctu.jvn.2023.151
Financial Time Series Trading using DDPG Considering Multi-scale Features
Chen, J., Liu, Z., Cai, X., Cai, Z., & Wang, W. (2023) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3594315.3594382
“The paper [14] uses deep neural networks for trading, in which the deep learning part automatically senses informative features of the market and the reinforcement learning module interacts with the deep representation and make”
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning (Extended Abstract)
Zhang, Y., Zhao, P., Wu, Q., Li, B., Huang, J., & Tan, M. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00312 · Cited by 1
“Most existing methods use handcraft features, such as moving average [2] and stochastic technical indicators [3], which, however, perform unsatisfactorily because of poor representation abilities [4].”
MethodNavigating Black Swan Events in Algorithmic Trading: A Reinforcement Learning Perspective
Díaz, F. V., & Guerrero-Mosquera, C. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230667
Assimilando a análise de sentimento no aprendizado por reforço para negociação inteligente.
Paiva, F. C. L. (2023) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.3.2023.tde-20102023-152926
Revolutionizing SET50 Stock Portfolio Management with Deep Reinforcement Learning
Thongkairat, S., Ponnoprat, D., Taninpong, P., & Yamaka, W. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46775-2_20
Deep learning techniques for real-time bitcoin prediction
Devi, P. M., Chandru, M., Jayaprathap, C., & Dinesh, V. (2023) · AIP conference proceedings · doi:10.1063/5.0173399
Annunziata, F. (2023) · Edward Elgar Publishing eBooks · doi:10.4337/9781035310722.00010
Algorithmic trading on financial time series using Deep Reinforcement LearningPreprint
Asghari, A., & Mozayani, N. (2024) · Research Square · doi:10.21203/rs.3.rs-3910354/v1
Pengaplikasian Deep Reinforcement Q-Learning Untuk Prediksi Perdagangan Valas Otomatis
Baradja, A., & Tjendrowasono, T. I. (2024) · Jurnal Rekayasa Sistem Informasi dan Teknologi · doi:10.59407/jrsit.v1i3.519 · Cited by 8
“Namun, untuk lingkungan perdagangan valas, variabel yang ada dalam dimensi waktu biasanya tidak dapat ditemukan dengan baik oleh kerangka kerja DQN [14].”
BackgroundAn End-to-End Direct Reinforcement Learning Approach for Multi-Factor Based Portfolio ManagementPreprint
Zhou, K., Huang, X., Chen, X., & Gao, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4729683
Stock Market’s Price Movement Prediction with Multi-branch LSTM and Technical Analysis
Xue, T., Qin, S., & Fu, Q. (2023) · International Conference on Neuromorphic Computing (ICNC) · doi:10.1109/icnc59488.2023.10462810
“In the study of using machine learning technology to predict stock market volatility, technical indicators are often used as part of the input characteristics to train the prediction model [17].”
MethodA novel portfolio strategy approach using deep reinforcement learning
Yang, X., Liu, C., Liu, J., & Yue, H. (2023) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1145/3650215.3650362
“Deng et al. [ 5 ] constructed a DDR trading system that can obtain reliable returns in the futures market, but the research object is a single futures product.”
BackgroundWITHDRAWN: Stock price prediction based on generative adversarial networkPreprint
Zhou, Y., Lin, Y., Hu, Z., Song, B., & Tang, J. (2024) · Research Square · doi:10.21203/rs.3.rs-4431730/v1
Portfolio Management of SET50 Stocks Using Deep Reinforcement Learning Methods
Kaewsompong, N., Saijai, W., & Thongkairat, S. (2024) · Studies in systems, decision and control · doi:10.1007/978-3-031-43601-7_15
Куликов, М. Л. (2024) · Bulletin of the South-Russian state technical University (NPI) Series Socio-economic Sciences · doi:10.17213/2075-2067-2024-2-130-137
Zheng, Z., Shao, J., Deng, S., Zhu, A., Shen, H. T., & Zhou, X. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00356 · Cited by 2
“Some studies [9], [17], [29], [30] incorporate deep learning to extract robust features in order to better represent the portfolio and optimize the investment return with RL.”
BackgroundA neural network architecture for maximizing alpha in a market timing investment strategyPreprint
Holguín, J. H. O., & Ospina, A. M. P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4898082
Continual Deep Reinforcement Learning for Financial Trading Using Bi-Directional Knowledge TransferPreprint
Katsikas, D., Passalis, N., & Tefas, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4907420
Zhong, R. (2024) · International Conference on Cryptography, Network Security and Communication Technology (CNSCT) · doi:10.1145/3673277.3673342
Wang, G., & Guo, G. (2024) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls61622.2024.10606876
Felizardo, L. K. (2024) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.3.2024.tde-26082024-093343
Asymmetric Graph-Based Deep Reinforcement Learning for Portfolio Optimization
Sun, H., Liu, X., Bian, Y., Zhu, P. F., Cheng, D., & Liang, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70378-2_11
Delayed MDPs with Feature Mapping
Dong, J., Wang, J., & Yang, L. F. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651374 · Cited by 1
“In real-world applications of modern RL, such as robotic control [2], autonomous vehicles [3], and financial trading [4], the agent cannot make proper actions solely based on the observation state due to the delayed feedback in the environment.”
BackgroundLearning to Play the Trading Game: Exploring Reinforcement Learning-Based Stock Trading Bots
Kulkarni, N., Ποτίκας, Π., & Potika, K. (2024) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice62917.2024.00011
“[9] and Lu [13] use real-time stock market data.”
BackgroundMethodInfluentialDeep Reinforcement Learning for Automated of Asian Stocks Trading
Panya, T., & Khamkong, M. (2024) · Studies in systems, decision and control · doi:10.1007/978-3-031-67770-0_37
Evolving Interpretable Fuzzy Rule-Based Systems with Genetic Programming for Predictive MaintenancePreprint
Sarikaya, F. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5017387
Two-Stage Separator Level Coupling Control Based on ASFW-DDPG Algorithm
He, X., Pang, H., Liu, B., & Chen, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3504739
“To improve the algorithm’s convergence speed, it incorporates the experience replay mechanism from DQN and employs strategic sampling to minimize data point correlations [27], [28], [29].”
Research on the Dynamic Hedging Trading Strategy for Portfolios Based on Deep Reinforcement Learning
Song, F., Liu, C., & Liu, J. (2024) · International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE) · doi:10.1109/icbase63199.2024.10762392 · Cited by 1
Enhancing efficiency in recurrent reinforcement learning for automated data-driven investment
Witkowski, T. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.435
Upadhyay, V., & Paul, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78107-0_4
Metadata
- Authors
- Deng, Y., Bao, F., Kong, Y., Ren, Z., & Dai, Q.
- Affiliations
- University of California, San Francisco (US)
- Tsinghua University (CN)
- Southeast University (CN)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2017-03
- Volume
- 28
- Issue
- 3
- Pages
- 653-664
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2344786740
- Cited by
- 822
- References
- 51
- Citations by year
- 2026: 90 · 2025: 90 · 2024: 95 · 2023: 110 · 2022: 109 · 2021: 100 · 2020: 98 · 2019: 76 · 2018: 40 · 2017: 10
- FWCI
- 47.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Project of the National Natural Science Foundation of China (61327902, 61120106003)
- National Science Foundation of Jiangsu Province, China (BK20150650)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- deep reinforcement learning, financial trading, recurrent neural networks, backpropagation through time, gradient vanishing, stock market, commodity futures, trading decision-making, representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.