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 401–500 of 822
Machine learning and behavioral economics for personalized choice architecturePreprint
Hrnjić, E., & Tomczak, N. (2019) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1907.02100 · Cited by 25
“[49] Yue Deng, Feng Bao, Youyong Kong, Zhiquan Ren, and Qionghai Dai, “Deep direct reinforcement learning for financial signal representation and trading,” IEEE Transactions on Neural Networks and Learning Systems 28, 653–664 (2016).”
BackgroundDirichlet policies for reinforced factor portfoliosPreprint
Andr\'e, E., & Coqueret, G. (2020) · RePEc: Research Papers in Economics · Cited by 7
DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and FuturePreprint
Dargazany, A. R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.13806 · Cited by 17
On-device synaptic memory consolidation using Fowler-Nordheim quantum-tunneling
Rahman, M., Bose, S., & Chakrabartty, S. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.1050585 · Cited by 10
“Thus, it is possible that improved backpropagation algorithms [20, 21] might be able to mitigate this artifact and in the process enhance the capacity and the performance of the FN-synapse network.”
BackgroundWang, L., Yang, H., Han, Y., Yin, S., & Wu, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127579 · Cited by 8
FedSlate: A Federated Deep Reinforcement Learning Recommender System
Deng, Y., Qiu, X., Tan, X., & Jin, Y. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3573250 · Cited by 12
“This method excels in scenarios requiring foresight, such as financial investment [33] and complex planning, due to its adeptness at managing delayed rewards.”
Self-citationStock Price Prediction Using Machine Learning Strategies
Chen, X. (2023) · BCP Business & Management · doi:10.54691/bcpbm.v36i.3507 · Cited by 11
A reinforcement learning algorithm for trading commodities
Giorgi, F., Herzel, S., & Pigato, P. (2023) · Applied Stochastic Models in Business and Industry · doi:10.1002/asmb.2825 · Cited by 6
Reinforcement Learning-Based Multimodal Model for the Stock Investment Portfolio Management Task
Du, S., & Shen, H.-L. (2024) · Electronics · doi:10.3390/electronics13193895 · Cited by 5
Portfolio Optimization using Deep Reinforcement Learning
Tamuly, A., Bhutani, G., & Sukriti, S. (2024) · IEEE India Council International Subsections Conference (INDISCON) · doi:10.1109/indiscon62179.2024.10744403 · Cited by 13
“Deng et al. (2016) [23] proposed a deep direct reinforcement learning approach for financial signal representation and trading, capable of extracting meaningful features from noisy financial data for profitable trading decisions.”
BackgroundFinancial Vision-Based Reinforcement Learning Trading Strategy
Tsai, Y., Szu, F.-M., Chen, J., & Chen, S. Y.-C. (2022) · Analytics · doi:10.3390/analytics1010004 · Cited by 6
AgentFuzz: Fuzzing for Deep Reinforcement Learning Systems
Li, T., Wan, X., & Özbek, M. M. (2022) · IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW) · doi:10.1109/issrew55968.2022.00049 · Cited by 7
“At the same time, the application of reinforcement learning has been extended to games such as games [7], autonomous driving [8], medical health [9], financial transactions [10], robot control [11] and network security [12] and many other fields, among which, many safety-critical fields are involved.”
BackgroundDeep Learning for Real Estate Trading
Zhao, Y., Chetty, G., & Tran, D. (2022) · IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) · doi:10.1109/csde56538.2022.10089222 · Cited by 6
“presented in [4, 6-12] and provides significantly improved investment strategy decision support after it”
BackgroundContrastive Learning and Reward Smoothing for Deep Portfolio Management
Lien, Y.-H., Li, Y.-K., & Wang, Y.-S. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/441 · Cited by 7
An optimized handwritten polynomial equations solver using an enhanced inception V4 model
Senthilkumar, S. S., Brindha, K., Chatterjee, J. M., Popat, A., Gupta, L., & Verma, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17574-1 · Cited by 6
“According to Dey et al. [15] the offline Odia handwritten character recognition issue has been addressed.”
Federated Learning for Data Trading Portfolio Allocation With Autonomous Economic Agents
Zhao, L., Cai, L., & Lu, W.-S. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3332315 · Cited by 7
“However, the dynamic nature of revenue returns in data trading poses significant challenges, making trading decisions complex and intricate [17], [18].”
BackgroundLussange, J., Vrizzi, S., Palminteri, S., & Gutkin, B. S. (2024) · PLoS ONE · doi:10.1371/journal.pone.0301141 · Cited by 10
“Even so, such studies confirm a trend of recent interest in reinforcement learning applied to financial MAS [28, 46–48] or order book models [49–51].”
BackgroundHrgović, I., & Pavić, I. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125017 · Cited by 6
Hierarchical Attention Network for Action Segmentation
Gammulle, H., Denman, S., Sridharan, S., & Fookes, C. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.01.023 · Cited by 9
“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…”
InfluentialNeural Network Model for Efficient portfolio Management and Time Series Forecasting
Pai, N., & Ilango, V. (2020) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs48265.2020.9121049 · Cited by 6
“Multiple inputs can be given to it and it then produces one output [13].”
BackgroundDetecting and Responding to Concept Drift in Business Processes
Yang, L., McClean, S. I., Donnelly, M. P., Burke, K., & Khan, K. (2022) · Algorithms · doi:10.3390/a15050174 · Cited by 6
Zhang, C., Li, Y., Chen, X., Jin, Y., Tang, P., & Li, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01265 · Cited by 6
Bai, F., Meng, F., Liu, J., Wang, J., & Meng, M. Q. ‐. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.08973 · Cited by 6
“Many problems can be represented in this form, such as game playing [15]–[17], autonomous driving [18]–[20], robot control [21], [22], recommended system [23] and trading [24].”
BackgroundA Primer on Artificial Intelligence and Machine Learning for the Financial Services IndustryPreprint
Osterrieder, J. R. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4349078 · Cited by 8
Share price prediction of aerospace relevant companies with recurrent neural networks based on PCA
Zheng, L., & He, H. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115384 · Cited by 41
Orra, A., Choudhary, H., Sharma, A., & Thakur, M. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02562-8 · Cited by 10
“The most common approach in the literature is to use a profit-based reward function for stock trading problems [44, 45].”
Revealing the Risk of Hyper-Parameter Leakage in Deep Reinforcement Learning Models
Du, L., Zhang, Z., Chen, M., Sun, M., Ji, S., Cheng, P., Chen, J., Backes, M., & Zhang, Y. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3611881 · Cited by 8
“DRL has also been applied to many complex decision-making tasks, such as autopilot [13], robot control [1], financial transactions [11], esports [7], [61], etc. DRLmodelgenerallyservesasaclosedboxduetothefactthat disclosing hidden details may render the model more susceptible to attacks from…”
Yu, J., & Chang, K. (2025) · International Journal of Financial Studies · doi:10.3390/ijfs13040227 · Cited by 8
“Other applications of DRL in stock trading include (Deng et al., 2017) which focused on financial signal representation and trading.”
Gaur, P., Singh, V. P., Varshney, T., Padmanaban, S., & Mathur, A. (2026) · Scientific Reports · doi:10.1038/s41598-025-33644-w · Cited by 5
“RL assisted automated trading and portfolio management are upgrading financial sector 10,11 .”
TRCC: Transferable Congestion Control With Reinforcement Learning
Zheng, Z., Xia, Z., Chou, Y.-C., & Chen, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3292371 · Cited by 5
“As a tool to solve sequential decision-making problems that target long-term aggregated benefits, reinforcement learning (RL) [9], [10], [11] has achieved great success in a variety of application areas, such as robotics, online games, finance, and automatic driving [12], [13].”
MethodReinforced Cost-Sensitive Graph Network for Detecting Fraud Leaders in Telecom Fraud
Gao, P., Li, Z., Zhou, D., & Zhang, L. (2024) · IEEE Access · doi:10.1109/access.2024.3448260 · Cited by 6
Price Prediction Using LSTM Based Machine Learning Models
Rahman, M. H., Nahid, S. I., Fahad, I. H. A., Nahid, F. M., & Khan, M. M. (2021) · IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) · doi:10.1109/iemcon53756.2021.9623120 · Cited by 5
Deep Learning Application in Stock Price Prediction
Wang, F., Liao, W., & Liang, S. (2021) · International Conference on Computer, Blockchain and Financial Development (CBFD) · doi:10.1109/cbfd52659.2021.00013 · Cited by 5
Robustness Analysis and Enhancement of Deep Reinforcement Learning-Based Schedulers
Zhang, S., Wang, C., & Zomaya, A. Y. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3218649 · Cited by 10
“It demonstrates human-level intelligence in various domains, such as games, robotics, self-driving cars, and finance [14], [15], [21], [22], [23], [24], [25].”
BackgroundPOE: A General Portfolio Optimization Environment for FinRL
Costa, C. D. S. B., & Costa, A. H. R. (2023) · Anais do II Brazilian Workshop on Artificial Intelligence in Finance (BWAIF 2023) · doi:10.5753/bwaif.2023.231144 · Cited by 6
“Furthermore, RL is able to handle brokerage fees (something supervised machine learning approaches have a hard time dealing with [Deng et al. 2017]), is very adaptable to unusual situations and can achieve effective behaviors even in the early stages of learning [Sutton and Barto 2018].”
BackgroundSmith, P., & Smith, L. (2023) · AI and Ethics · doi:10.1007/s43681-023-00388-0 · Cited by 9
“The continuous evolution of AI techniques has led to its widespread adoption in fields such as healthcare [28], finance [10] and autonomous vehicles [17].”
Consigli, G., Gomez, A. A., & Zubelli, J. P. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108599 · Cited by 5
Discriminant Kernel Assignment for Image Coding
Deng, Y. C., Zhao, Y., Ren, Z., Kong, Y., Bao, F., & Dai, Q. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2547941 · Cited by 5
“DL system is always built on an extremely complicated neural network involving tons of hidden parameters to be fitted from training data [6].”
BackgroundSelf-citationOnline sequential extreme learning machine with the increased classes
Yu, H., Xie, H., Yang, X., Zou, H., & Gao, S. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107008 · Cited by 7
A Trend-based Stock Index Forecasting Model with Gated Recurrent Neural Network
Liu, Y., & Liu, X. (2018) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic.2018.8706267 · Cited by 6
“Deep recurrent neural network was used to identify the characteristics of real-time financial signals, proved that it has good robustness in stock market and commodity futures market[5].”
MethodDesign and Research of Intelligent Quantitative Investment Model Based on PLR-IRF and DRNN Algorithm
Tang, C., Zheng, X., Yu, X., Chen, C., & Zhu, W. (2018) · IEEE Information Technology and Mechatronics Engineering Conference (ITOEC) · doi:10.1109/itoec.2018.8740741 · Cited by 4
“Then according to the Deep Learning (DL) theory, which adopts a Deep Recursive Neural Network (DRNN) to design the investment decision model.”
MethodInfluentialGated Value Network for Multilabel Classification
Hou, Y., Wan, S., Bao, F., Ren, Z., Dong, Y., Dai, Q., & Deng, Y. C. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3019804 · Cited by 5
Self-citationA Review of LLM Agent Applications in Finance and BankingPreprint
Batra, D., Hamill, C. B., Hartley, J., Okhrati, R., Seddon, D., Miller, H., Khraishi, R., & Cowan, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5381584 · Cited by 15
MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading
Zong, C., Wang, C., Qin, M., Feng, L., Wang, X., & An, B. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3672064 · Cited by 11
“However, although RL has achieved great performance in low-frequency trading [5, 25, 30], there remains a technical gap in developing effective high-frequency trading algorithms for cryptocurrency markets because of long trading horizons and volatile market fluctuations.”
BackgroundStrategy allocation for financial trading using competitive reinforcement learning and fuzzy logic
Huang, J.-C., Chen, C.-T., Chang, C.-C., & Huang, S.-H. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113927 · Cited by 4
Imandojemu, K., Osabohien, R. A., Al‐Faryan, M. A. S., & Odebunmi, S. T. (2025) · Development and sustainability in economics and finance. · doi:10.1016/j.dsef.2025.100104 · Cited by 4
Pairs Trading Strategy Optimization Using Proximal Policy Optimization Algorithms
Chen, Y., Shih, W.-Y., Lai, H.-C., Chang, H., & Huang, J. (2023) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp57234.2023.00015 · Cited by 11
“– Previous action (at−1): at−1 means the action selected at the last timestamp which is used for avoiding frequent change of decisions [29].”
BackgroundMoustakidis, V., Passalis, N., & Tefas, A. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.10.005 · Cited by 5
Fu, Y.-T., & Huang, W.-C. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113264 · Cited by 4
Adedigba, D. A., Agbolade, D., & Hasan, R. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00519-y · Cited by 6
“Automated trading systems are becoming more prevalent in their dependence on algorithmic decision-making logic, with hedge funds and institutional investors allocating substantial sums of money in quantitative trading strategies [9].”
Beyond Discounted Returns: Robust Markov Decision Processes with Average and Blackwell Optimality
Grand-Clément, J., Petrik, M., & Vieille, N. (2026) · Operations Research · doi:10.1287/opre.2023.0694 · Cited by 20
Nalmpantis, A., Passalis, N., Tsantekidis, A., & Tefas, A. (2021) · Machine learning for signal processing ... · doi:10.1109/mlsp52302.2021.9596155 · Cited by 6
Ghost Expectation Point with Deep Reinforcement Learning in Financial Portfolio Management
Yang, X., Sun, R., Ren, X., Stefanidis, A., Gu, F., & Su, J. (2022) · International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) · doi:10.1109/cyberc55534.2022.00030 · Cited by 4
“[12].”
Wang, X., Shi, X., Chen, J., Guo, X., & Li, D. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e26474 · Cited by 6
“Almahdi and Yang [21] introduced an adaptive-capacity deep reinforcement learning system centered on transactions, while Deng et al. applied deep reinforcement learning to single financial asset trading, yielding reliable returns in the futures market [22].”
Trading Strategy of the Cryptocurrency Market Based on Deep Q-Learning Agents
Huang, C. S. J., & Su, Y.-S. (2024) · Applied Artificial Intelligence · doi:10.1080/08839514.2024.2381165 · Cited by 8
“Deng et al. (2016) represented financial signals as fuzzy deep direct reinforcement models.”
DeepBonds: A Deep Learning Approach to Predicting United States Treasury Yield
Ying, J. J.-C., Wang, Y., Chang, C., Chang, C.-W., Chen, Y.-H., & Liou, Y.-S. (2019) · International Conference on Ubi-Media Computing (UMEDIA) · doi:10.1109/ubi-media.2019.00055 · Cited by 5
Latent Segmentation of Stock Trading Strategies Using Multi-Modal Imitation Learning
Maeda, I., deGraw, D., Kitano, M., Matsushima, H., Izumi, K., Sakaji, H., & Kato, A. (2020) · Journal of risk and financial management · doi:10.3390/jrfm13110250 · Cited by 5
A Survey on Deep Learning in Financial Markets
Zhang, J., Zhai, J., & Wang, H. (2021) · Financial Mathematics and Fintech · doi:10.1007/978-981-15-8373-5_3 · Cited by 4
Hamori, S., & Takiguchi, T. (2020) · MDPI eBooks · doi:10.3390/books978-3-03936-225-7 · Cited by 7
Deep adaptive group-based input normalization for financial trading
Nalmpantis, A., Passalis, N., Tsantekidis, A., & Tefas, A. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.11.004 · Cited by 4
Forecasting Stock Market Using Machine Learning Approach Encoder-Decoder ConvLSTM
Iqbal, K., Hassan, A., Hassan, S. S. M. U., Iqbal, S., Aslam, F., & Mughal, K. S. (2021) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit53504.2021.00018 · Cited by 4
Online Knowledge Distillation for Financial Timeseries Forecasting
Floratos, P., Tsantekidis, A., Passalis, N., & Tefas, A. (2022) · International Conference on Innovations in Intelligent Systems and Applications (INISTA) · doi:10.1109/inista55318.2022.9894138 · Cited by 4
“this end, ranging from supervised learning approaches using Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) [8], [9] to Deep Reinforcement Learning (DRL) methodologies [10], [11].”
MethodStock Market Investment Strategy Using Deep-Q-Learning Network
Sudhakar, K., & Naganjaneyulu, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36402-0_45 · Cited by 4
Takale, D. G., Wattamwar, A. A., Saipatwar, S. S., Saindane, H. V., & Patil, T. (2024) · Journal of Firewall Software and Networking · doi:10.48001/jofsn.2024.211-10 · Cited by 4
Skeepers, T., van Zyl, T. L., & Paskaramoorthy, A. (2021) · International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi53840.2021.9654987 · Cited by 4
Thakkar, P., Oza, V., & Thesia, Y. (2022) · International Journal of Computational Science and Engineering · doi:10.1504/ijcse.2022.120784 · Cited by 5
Reinforcement Learning with Expert Trajectory For Quantitative TradingPreprint
Chen, S., Luo, W., & Yu, C. (2021) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2105.03844 · Cited by 7
“In the testing stage, however, the real reward of the agent is used to measure the performance of the proposed method [5].”
MethodReinforcement Learning in Quantitative Trading: A SurveyPreprint
Alameer, A., Saleh, H., & Alshehri, K. A. (2022) · doi:10.36227/techrxiv.19303853.v1 · Cited by 7
Braga, J., Regateiro, F. S., Stiubiener, I., & Braga, J. C. (2023) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/wexjr · Cited by 6
Proceedings of The ACM Collective Intelligence Conference
(2023) · doi:10.1145/3582269 · Cited by 4
Нейросетевые подходы и методы моделирования финансовых рынков
Kosnikov, S. N., Полещук, М. А., & Джамалян, А. Г. (2024) · Industrial Economics · doi:10.47576/2949-1886.2024.27.47.012 · Cited by 3
A Deep Learning Approach to Goal-Based Portfolio Optimization in Non-Stationary Environments
Bauman, T., Mrčela, L., Goluža, S., & Kostanjčar, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3588247 · Cited by 4
“The application to optimal execution, a problem of buying or selling a specific amount of an asset in a given timeframe, was explored in [8], [9], and [10].”
CMCPS: A model copyright protection scheme based on Cohen's Kappa statistic
Ren, J., & Niu, Z. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106775 · Cited by 3
Zhou, K., Huang, X., Chen, X., & Gao, J. (2025) · European Journal of Finance · doi:10.1080/1351847x.2025.2558114 · Cited by 5
“1 One advantage of DRL is its provision of a flexible framework that combines neural networks with various trading and portfolio decision models (Deng et al. 2017).”
Ma, C., Gao, F., Ji, L.-Z., Zhang, C., Long, L.-H., & Zhang, J.-S. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114269 · Cited by 5
Liu, Y.-K., Pan, Y., Lu, P.-F., Tsai, Y., & Chen, S. Y.-C. (2025) · IEEE International Conference on Quantum Computing and Engineering (QCE) · doi:10.1109/qce65121.2025.10325 · Cited by 3
“Reinforcement learning (RL), by framing trading as a sequential decision-making problem, has emerged as a robust framework for learning adaptive strategies directly from market data [3], [4].”
Toward Robust Agents: A Survey of Adversarial Attacks and Defenses in Deep Reinforcement Learning
Mohan, A., & Schön, T. (2026) · IEEE Access · doi:10.1109/access.2026.3657855 · Cited by 7
“Financial markets leverage DRL for algorithmic trading under complex market dynamics [23], while smart grid management and wireless communications benefit from DRL-enabled resource allocation [24].”
A hybrid adaptive trading strategy integrating investor sentiment for precious metal ETFs
Novotný, J., & Hajek, P. (2026) · Financial Innovation · doi:10.1186/s40854-026-00911-2 · Cited by 4
“Deng et al. (2017) present a deep direct reinforcement learning method that actively learns trading signals from raw price data.”
Wafi, A. S., El-Halaby, S. I., & Ahmed, H. (2026) · Journal of risk and financial management · doi:10.3390/jrfm19030228 · Cited by 5
“Deep learning architectures such as convolutional neural networks (CNNs) and LSTMs capture temporal patterns (Fischer & Krauss, 2018; Gu et al., 2020), while reinforcement learning enables adaptive trading strategies (Deng et al., 2016).”
Yıldırım, H., Karadeniz, Y., & Doğan, M. (2026) · Sustainable Development · doi:10.1002/sd.71066 · Cited by 3
Recent Advances on Off-Policy Reinforcement Learning for Optimization Control
Luo, B., Liu, D., Wu, H.-N., Huang, T., Yang, C., & Gui, W. (2026) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2026.3683384 · Cited by 4
“It has been widely applied in many areas, e.g., robotics [4], autonomous driving [5], high-speed aircraft [6], protein architecture design [7], healthcare [8], natural language processing [9], finance [10], etc.”
DRL Trading with CPT Actor and Truncated Quantile Critics
Foo, M. J. R., Lesmana, N. S., & Pun, C. S. (2023) · International Conference on AI in Finance · doi:10.1145/3604237.3626886 · Cited by 5
“The DRL models adopted range from critic-only [8, 12, 19], actor-only [14, 20, 33], actor-critic [4, 21, 27], to some ensemble of different algorithms [51].”
MethodTransformer-Based Reinforcement Learning for Forex Trading
Jayanthi, P., Kumar, K. R. N., Kumar, C. R., Hemanth, D. J., Bhama, P. R. K. S., & Mercy, P. (2024) · Algorithms for intelligent systems · doi:10.1007/978-981-97-3526-6_14 · Cited by 3
A Neural Network Architecture for Maximizing Alpha in a Market Timing Investment Strategy
Holguín, J. H. O., & Ospina, A. M. P. (2024) · IEEE Access · doi:10.1109/access.2024.3446708 · Cited by 3
“This cost was on the lower end of the spectrum in the financial literature toward 2000 [47], but it has also been used as a more recent minimum benchmark in modern reinforcement learning studies on finance [13], [53].”
BackgroundMethodDeep Learning Models in Finance: Past, Present, and Future
Vishnumolakala, S. K., Gopu, S. R., Dash, J. K., Tripathy, S., & Singh, S. (2024) · Intelligent systems reference library · doi:10.1007/978-3-031-61037-0_21 · Cited by 4
Optimized Automated Stock Trading using DQN and Double DQN
Bharadwaj, G. S., Pratap, D., & Darapaneni, N. (2024) · International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) · doi:10.1109/iacis61494.2024.10721810 · Cited by 5
“In [7], Deng et.al propose using an actor-based RL method instead of Q-learning for action selection.”
MethodHuang, L., Leng, H., Song, J., Wang, D., Wang, W., Hu, R., & Cao, H. (2025) · Applied Sciences · doi:10.3390/app15126399 · Cited by 3
Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning
Wang, Y., Xiao, P., Ban, H., Ji, K., & Zou, S. (2025) · IEEE Transactions on Information Theory · doi:10.1109/tit.2025.3581454 · Cited by 7
“R EINFORCEMENT learning (RL) has made much progress in a variety of applications, such as autonomous driving, robotics manipulation, and financial trades [1], [2], [3].”
PortfolioZero: A stock portfolio model based on deep reinforcement learning
Li, H., & Hai, M. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113578 · Cited by 4
Attention-enhanced reinforcement learning for dynamic portfolio optimization
Xue, P., & Ye, Y. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200622 · Cited by 14
A General Framework of Optimal Investment
Zhang, L. (2019) · Journal of Mathematical Finance · doi:10.4236/jmf.2019.93028 · Cited by 4
“Applications of reinforcement learning on portfolio management can be found in [18], [21], [22], [30] and [31].”
Roy, G., Fiaidhi, J., & Mohammed, S. (2022) · Artificial Intelligence Evolution · doi:10.37256/aie.3220221722 · Cited by 4
“[29] Deng Y, Bao F, Kong Y, Ren Z, Dai Q.”
BackgroundMethodActor-Critic Methods in Stock Trading : A Comparative Study
Khemlichi, F., Elfilali, H. E., Chougrad, H., Ali, S. E. B., & Khamlichi, Y. I. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10253277 · Cited by 4
Development of recurrent neural networks for price forecasting at cryptocurrency exchanges
Tyshchenko, V., Ачкасова, С., Найденко, О., Kanyhin, S., & Карпова, В. (2023) · Eastern-European Journal of Enterprise Technologies · doi:10.15587/1729-4061.2023.287094 · Cited by 4
“However, early RNN iterations encountered the ‘vanishing gradient’ issue, leading to protracted training durations for gradient methods when working with RNNs [14, 15].”
MethodLEVER: Online Adaptive Sequence Learning Framework for High-Frequency Trading
Yuan, Z., Liu, J., Zhou, H., Zhang, D., Liu, H., Zhu, N., & Xiong, H. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3336185 · Cited by 5
“Therefore, it remains a challenge to utilize these handcraft technical indicators that naturally lack generalization ability in producing trustworthy SRLs to quantify the real market balance in noise [4].”
BackgroundMethodInfluentialUncertainty in Bayesian Reinforcement Learning for Robot Manipulation Tasks with Sparse Rewards
Zheng, L., Li, Y., Wang, Y., Bai, G., He, H., & Dong, E. (2023) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio58561.2023.10354785 · Cited by 3
“Reinforcement learning (RL) has emerged as a promising approach for training autonomous agents to perform complex tasks in various domains[1], [2], [3], [4], especially including robotics manipulation tasks such as grasping[5], tool assembly[6] and human-robot interaction[7].”
BackgroundNavigation for autonomous vehicles via fast-stable and smooth reinforcement learning
Zhang, R., Yang, J., Liang, Y., Lu, S., Dong, Y., Yang, B., & Zhang, L. (2023) · Science China Technological Sciences · doi:10.1007/s11431-023-2483-x · Cited by 3
ISLAMIC STOCK PORTFOLIO OPTIMIZATION USING DEEP REINFORCEMENT LEARNING
Faturohman, T., & Nugraha, T. (2022) · Journal of Islamic Monetary Economics and Finance · doi:10.21098/jimf.v8i2.1430 · Cited by 12
A General Framework on Enhancing Portfolio Management with Reinforcement Learning
Li, Y., Wang, J., & Cao, Y. (2024) · International Conference on Computers in Management and Business (ICCMB) · doi:10.1145/3647782.3647801 · Cited by 12
“Portfolio optimization remains one of the most challenging problems in finance, involving the continuous reallocation of funds across different financial products to maximize returns while managing risks [1, 2, 16].”
BackgroundMethodBialkova, S. (2024) · Springer eBooks · doi:10.1007/978-3-031-56471-0_10 · Cited by 3
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.