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 201–300 of 822
Q-Learning-Based Adaptive Power Control in Wireless RF Energy Harvesting Heterogeneous Networks
Zhang, R., Xiong, K., Guo, W., Yang, X. C., Fan, P., & Letaief, K. B. (2020) · IEEE Systems Journal · doi:10.1109/jsyst.2020.3015386 · Cited by 29
“MIMO [32], and wireless body area networks (WBANs) [33], since ML enables adaptive learning and decision making in dynamic or fast-changing environments [31]–[37].”
BackgroundTwo-Stage Bayesian Optimization for Scalable Inference in State-Space Models
Imani, M., & Ghoreishi, S. F. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3069172 · Cited by 30
“MODELING, learning, and decision-making are becoming critical parts of our everyday’s lives, including robotics [1], healthcare [2], smart grids [3], finance [4], self-driving cars [5], and many more.”
BackgroundModel-Based Transfer Reinforcement Learning Based on Graphical Model Representations
Sun, Y., Zhang, K., & Sun, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3107375 · Cited by 28
DiffPrep: Differentiable Data Preprocessing Pipeline Search for Learning over Tabular Data
Li, P., Chen, Z., Chu, X., & Rong, K. (2023) · Proceedings of the ACM on Management of Data · doi:10.1145/3589328 · Cited by 56
A Reinforcement Learning Approach for Continuum Robot Control
Kargin, T. C., & Kołota, J. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-02003-0 · Cited by 36
“RL and Deep RL are used in a variety of academic and commercial contexts, including robotics [16–19], autonomous vehicles [20], banking [21], smart grids [22], and the energy sector [23].”
Chen, C.-H., & Liu, C. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2772870 · Cited by 27
“In contrast to supervise learning, reinforcement learning [21]–[26] does not rely on training data to train NFCs.”
BackgroundBridging the Gap Between Markowitz Planning and Deep Reinforcement LearningPreprint
Benhamou, E., Saltiel, D., Ungari, S., & Mukhopadhyay, A. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3702112 · Cited by 36
Deep Reinforcement Learning for Active High Frequency TradingPreprint
Briola, A., Turiel, J., Marcaccioli, R., Cauderan, A., & Aste, T. (2021) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2101.07107 · Cited by 76
Hazrathosseini, A., & Afrapoli, A. M. (2024) · Mining Technology Transactions of the Institutions of Mining and Metallurgy · doi:10.1177/25726668231222998 · Cited by 43
“RL ’ s versatility and potential for wide-ranging applications are showcased in various domains such as robotics (Ibarz et al., 2021), board games (Silver et al., 2016), automated driving (An and Jung, 2019), vehicle routing (Zhao et al., 2020), and fi nance (Deng et al., 2016).”
BackgroundLearning to Trade with Deep Actor Critic Methods
Li, J., Rao, R., & Shi, J. (2018) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2018.10116 · Cited by 27
“[6] explain the traditional recurrent reinforcement learning process as a one-layer recurrent neural network and enhance it with a deep network.”
BackgroundMethodZhang, H.-C., Wu, Q., & Li, F.-Y. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108754 · Cited by 26
Single-step deep reinforcement learning for two- and three-dimensional optimal shape design
Ghraieb, H., Viquerat, J., Larcher, A., Méliga, P., & Hachem, E. (2022) · AIP Advances · doi:10.1063/5.0097241 · Cited by 26
Portfolio dynamic trading strategies using deep reinforcement learning
Day, M.-Y., Yang, C.-Y., & Ni, Y. (2023) · Soft Computing · doi:10.1007/s00500-023-08973-5 · Cited by 26
“Reinforcement learning is frequently used in financial signal representation (Deng et al. 2017; Taghian et al. 2022), trading (Chen and Huang 2021; Zhang et al. 2020), and portfolio management (Betancourt and Chen 2021; Ozbayoglu et al. 2020).”
Cloning Strategies from Trading Records using Agent-based Reinforcement Learning Algorithm
Chen, C.-T., Chen, A., & Huang, S.-H. (2018) · IEEE International Conference on Agents (ICA) · doi:10.1109/agents.2018.8460078 · Cited by 26
“[7] combined deep learning and reinforcement learning in the issue for financial assert trading.”
BackgroundNews-driven stock prediction via noisy equity state representation
Huang, H., Liu, X., Zhang, Y., & Feng, C. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.092 · Cited by 28
“Some work models the correlations among different stocks by pre-defined correlation graph [20], tensor factorization [21], reinforcement learning [22,23], dynamic financial distress prediction models [24] and graph convolutional networks [25,8].”
MethodPark, D.-Y., & Lee, K. (2021) · IEEE Access · doi:10.1109/access.2021.3127209 · Cited by 30
“To accommodate these challenges, recent methods [1]–[6] use deep reinforcement learning and deliver good performance in terms of profitability.”
BackgroundMethodLiu, J., & Kang, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121373 · Cited by 38
Risk-Sensitive Deep Reinforcement Learning for Portfolio Optimization
Wang, X., & Liu, L. (2025) · Journal of risk and financial management · doi:10.3390/jrfm18070347 · Cited by 32
Equal risk pricing of derivatives with deep hedging
Carbonneau, A., & Godin, F. (2020) · Quantitative Finance · doi:10.1080/14697688.2020.1806343 · Cited by 27
Wang, X., Wang, L., Dong, C., Ren, H., & Xing, K. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3237580 · Cited by 24
“Deng et al. [42] introduced a recurrent deep neural network for real-time financial signal representation and trading and designed a model based on two biological-related learning concepts of deep learning and reinforcement learning.”
A Mean-VaR Based Deep Reinforcement Learning Framework for Practical Algorithmic Trading
Jin, B. (2023) · IEEE Access · doi:10.1109/access.2023.3259108 · Cited by 31
“These two parts are coupled in classical algorithms such as PG [16], [18] and DQN [32], [33], [34], making the training process very time-consuming.”
BackgroundMethodInfluentialXu, X., Cao, Y., Cai, P., Zhang, W., & Chen, H. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.116890 · Cited by 25
Derivatives Pricing via Machine Learning
Ye, T., & Zhang, L.-L. (2019) · Journal of Mathematical Finance · doi:10.2139/ssrn.3352688 · Cited by 19
“…asset pricing, reinforcement learning and Q-learning in solving dynamic programming problems such as optimal investment-consumption choice, option pricing and optimal trading strategies construction, e.g., [18], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28] and references therein.”
Investor-Imitator: A Framework for Trading Knowledge Extraction
Ding, Y. C., Liu, W., Bian, J., Zhang, D., & Liu, T. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3220113 · Cited by 23
“Recently, [10] researched the policy function incorporated in RRL, it took the advantages from a deep feature representation with a fuzzy feature transform layer, and tried to fully exploit the feature information.”
BackgroundForecasting Financial Time Series Using Robust Deep Adaptive Input Normalization
Passalis, N., Kanniainen, J., Gabbouj, M., Iosifidis, A., & Tefas, A. (2021) · Journal of Signal Processing Systems · doi:10.1007/s11265-020-01624-0 · Cited by 24
Blind decision making: Reinforcement learning with delayed observations
Agarwal, M., & Aggarwal, V. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.06.022 · Cited by 41
Mikkilä, O., & Kanniainen, J. (2021) · Quantitative Finance · doi:10.1080/14697688.2022.2136037 · Cited by 55
“Deep Reinforcement Learning (DRL) has shown its potential automated trading (Deng et al. 2016).”
He, F., Chen, C.-T., & Huang, S.-H. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.109985 · Cited by 25
A Reinforcement Learning-Based QAM/PSK Symbol Synchronizer
Matta, M., Cardarilli, G. C., Nunzio, L. D., Fazzolari, R., Giardino, D., Nannarelli, A., Re, M., & Spanò, S. (2019) · IEEE Access · doi:10.1109/access.2019.2938390 · Cited by 24
“RL became increasingly popular in robotics [28]–[31], Internet of Things (IoT) [32], financial trading [33] and industrial applications [34].”
BackgroundResearch on Maneuvering Decision Algorithm Based on Improved Deep Deterministic Policy Gradient
Jing, X., Hou, M., Wu, G., Ma, Z., & Tao, Z. (2022) · IEEE Access · doi:10.1109/access.2022.3202918 · Cited by 23
“[30] proposed a DDPG algorithm based on the 450 actor-critic framework [43] through the transformation of the 451 deterministic policy gradient (DPG) [44] method, which can 452 be used to solve the DRL problemswith the continuous action 453 space and state space.”
MethodHao, Z., Maio, F. D., & Zio, E. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109231 · Cited by 25
Wang, S., JunHui, M., Zhao, Z.-M., Yang, H.-Z.-Y., Xuan, Y., Ouyang, J.-X., Fan, D.-M., Yu, J., & Wang, X. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120351 · Cited by 23
A Noise-Sensitivity-Analysis-Based Test Prioritization Technique for Deep Neural NetworksPreprint
Zhang, L., Sun, X., Li, Y., & Zhang, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.00054 · Cited by 33
“Deep learning [1] have been used in the fields including molecular genetic studies [2], brain science [3], drug discovery [4], medical diagnosis [5], mobile application [6], financial transaction [7], and so on.”
MethodEvaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks
Lee, S., Song, W., Jana, S., Cha, M., & Son, S. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3196790 · Cited by 27
“The recent advent of deep neural networks (DNNs) has accelerated the development and application of diverse DNN models across various domains, including image search [23, 55], security [58, 59], finance [18, 20], and self-driving vehicles [52].”
BackgroundA turning point prediction method of stock price based on RVFL-GMDH and chaotic time series analysis
Chen, J., Yang, S., Zhang, D., & Nanehkaran, Y. A. (2021) · Knowledge and Information Systems · doi:10.1007/s10115-021-01602-3 · Cited by 21
“[23] trained a recurrent deep neural network (NN) for real-time financial signal representation and trading; the experimental results on both the stock and the commodity future markets demonstrated the effectiveness of their proposed approach.”
BackgroundAuto uning of price prediction models for high-frequency trading via reinforcement learning
Zhang, W., Zhang, N., Yan, J., Li, G., & Yang, X. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108543 · Cited by 21
Cardinality Constrained Portfolio Optimization via Alternating Direction Method of Multipliers
Shi, Z.-L., Li, X. P., Leung, C.-S., & So, H. C. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3192065 · Cited by 22
Guarino, A., Grilli, L., Santoro, D., Messina, F., & Zaccagnino, R. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07543-4 · Cited by 23
“[29], starting from the idea that computers can beat experienced traders, proposed a recurrent neural network (RNN) for sensing the dynamic market condition for feature learning and combined it with a RL framework that makes trading decisions.”
BackgroundUsing Deep Reinforcement Learning with Hierarchical Risk Parity for Portfolio Optimization
Millea, A., & Edalat, A. (2022) · International Journal of Financial Studies · doi:10.3390/ijfs11010010 · Cited by 30
Predicting Chinese Commodity Futures Price: An EEMD-Hurst-LSTM Hybrid Approach
Huang, K., Zhang, Z., Li, Q., & Luo, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3239924 · Cited by 28
“Reference [14] combined DNN and reinforcement learning (RL) to use fuzzy deep direct reinforcement learning (FDDR) for prediction and transaction signal generation.”
MethodReinforcement learning for patient-specific optimal stenting of intracranial aneurysms
Hachem, E., Méliga, P., Goetz, A., Rico, P. J., Viquerat, J., Larcher, A., Valette, R., Fava-Sanches, A., Lannelongue, V., Ghraieb, H., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-34007-z · Cited by 24
Learning Dynamic Dependencies With Graph Evolution Recurrent Unit for Stock Predictions
Tian, H., Zhang, X., Zheng, X., & Zeng, D. D. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2023.3284840 · Cited by 29
A Multi-Scale Temporal Feature Aggregation Convolutional Neural Network for Portfolio Management
Shi, S., Li, J., Li, G., & Pan, P. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357961 · Cited by 31
Dynamics-Enabled Safe Deep Reinforcement Learning: Case Study on Active Suspension Control
Li, Z., Chu, T., & Kalabic, U. V. (2019) · IEEE Conference on Control Technology and Applications (CCTA) · doi:10.1109/ccta.2019.8920696 · Cited by 22
“The past decades have witnessed the great success of reinforcement learning (RL) in a broad spectrum of applications such as board games [1], [2], natural language processing [3], [4], economics [5], [6], among many others.”
Leem, J., & Kim, H. Y. (2020) · PLoS ONE · doi:10.1371/journal.pone.0236178 · Cited by 25
“Although trading systems research based on RL is actively conducted, there are many challenges, such as difficulties in analyzing and training, which arise from insufficient data or excessive noise [4].”
BackgroundMethodInfluentialDabérius, K., Granat, E., & Karlsson, P. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3374766 · Cited by 40
Stock Market Trading Based on Market Sentiments and Reinforcement Learning
Suhail, K. M. A., Sankar, S. S., Kumar, A. S., Tsafack, N., Soliman, N. F., Algarni, A. D., El‐Shafai, W., & El‐Samie, F. E. A. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.017069 · Cited by 21
“[29] presented a deep neural network with an AE to learn the input vector deep representation.”
BackgroundRelational Temporal Graph Convolutional Networks for Ranking-Based Stock Prediction
Zheng, Z., Shao, J., Zhu, J., & Shen, H. T. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00017 · Cited by 21
“Besides, these handcraft indicators are often criticized for their poor generalization capacity [15].”
BackgroundFuzzy Categorical Deep Reinforcement Learning of a Defensive Game for an Unmanned Surface Vessel
Cheng, Y., Sun, Z., Huang, Y., & Zhang, W. (2019) · International Journal of Fuzzy Systems · doi:10.1007/s40815-018-0586-0 · Cited by 21
“Therefore, RL occupies an important role in the field of modern data analysis and data mining [19, 20].”
BackgroundA new discriminative collaborative representation-based classification method via l2 regularizations
Gou, J., Hou, B., Yuan, Y., Ou, W., & Zeng, S. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04460-x · Cited by 20
Portfolio Optimization with 2D Relative-Attentional Gated Transformer
Kim, T. W., & Khushi, M. (2020) · IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) · doi:10.1109/csde50874.2020.9411635 · Cited by 20
“Several researchers [10, 11] used reinforcement learning with discrete action space, simplifying trading actions to include buying, selling, or holding a single asset.”
A Deep Deterministic Policy Gradient-based Strategy for Stocks Portfolio Management
Zhang, H., Jiang, Z., & Su, J. (2021) · IEEE International Conference on Big Data Analytics (ICBDA) · doi:10.1109/icbda51983.2021.9403049 · Cited by 27
Uncertainty-Aware Portfolio Management With Risk-Sensitive Multiagent Network
Park, K.-H., Jung, H. G., Eom, T.-S., & Lee, S.-W. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3174642 · Cited by 21
“In particular, as the purpose of PM is to satisfy the demands of investors by sequentially rebalancing portfolios, reinforcement learning (RL) has been popularly used [4]–[6].”
BackgroundEmpirical Analysis of Automated Stock Trading Using Deep Reinforcement Learning
Kong, M., & So, J. (2023) · Applied Sciences · doi:10.3390/app13010633 · Cited by 28
Human-aligned trading by imitative multi-loss reinforcement learning
Ye, Z. J., & Schuller, B. W. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120939 · Cited by 20
Selective transfer learning with adversarial training for stock movement prediction
Li, Y., Dai, H., & Zheng, Z. (2022) · Connection Science · doi:10.1080/09540091.2021.2021143 · Cited by 26
“The work (Deng et al., 2017) introduced a fuzzy learning system for input data to reduce noise.”
BackgroundCross-Domain Deep Learning Approach For Multiple Financial Market Prediction
Jiang, X., Pan, S., Jiang, J. B., & Long, G. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489360 · Cited by 22
“They have recently attracted growing interest in financial market prediction [6] [7] [8] [9].”
BackgroundOnline deep learning’s role in conquering the challenges of streaming data: a survey
Sulaiman, M. A., Farmanbar, M., Kagami, S., Belbachir, A. N., & Rong, C. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02351-3 · Cited by 26
“In algorithmic trading, online learning models can optimize trading strategies by learning from real-time data [124].”
Deep Reinforcement Learning based Multi-Objective Systems for Financial Trading
Bisht, K., & Kumar, A. (2020) · IEEE International Conference on Recent Advances and Innovations in Engineering (ICRAIE) · doi:10.1109/icraie51050.2020.9358319 · Cited by 19
“Then after the development of reinforcement learning [2] researchers found more effective technique to train the trading systems [17], [18], [19].”
MethodResultInfluentialWang, C., Han, C., Guo, T., & Ding, M. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03453-z · Cited by 22
Forecasting financial signal for automated trading: An interpretable approach
Roostaee, M. R., & Abin, A. A. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118570 · Cited by 18
Distributed Multi-agent Target Search and Tracking With Gaussian Process and Reinforcement Learning
Kim, J., Jang, D., & Kim, H. J. (2023) · International Journal of Control Automation and Systems · doi:10.1007/s12555-022-0555-0 · Cited by 20
“Recent advances in data-driven techniques such as deep learning have extended the reach of RL to various domains [19-22].”
BackgroundAlgorithmic trading using combinational rule vector and deep reinforcement learning
Huang, Z., Li, N., Mei, W., & Gong, W. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110802 · Cited by 19
Reinforcement Learning-Based Dynamic Order Recommendation for On-Demand Food Delivery
Wang, X., Wang, L., Dong, C., Ren, H., & Xing, K. (2023) · Tsinghua Science & Technology · doi:10.26599/tst.2023.9010041 · Cited by 21
Park, J.-H., Kim, J., & Huh, J. (2024) · IEEE Access · doi:10.1109/access.2024.3361035 · Cited by 28
“Deng et al. [25] showed that using deep neural networks can generate more benefits.”
BackgroundZhang, W., Zhao, Y., Sun, S., Ying, J., Xie, Y., Song, Z., Wang, X., & An, B. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645615 · Cited by 28
“In fact, RL has achieved significant success in various quantitative trading tasks such as algorithmic trading [4], portfolio management [31], order execution [8] and market making [26].”
BackgroundDisguise Adversarial Networks for Click-through Rate Prediction
Deng, Y. C., Shen, Y., & Jin, H. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/220 · Cited by 19
Self-citationMulti-Step-Ahead Stock Market Prediction Based on Least Squares Generative Adversarial Network
Faraz, M., & Khaloozadeh, H. (2020) · Iranian Conference on Electrical Engineering · doi:10.1109/icee50131.2020.9260858 · Cited by 18
“In [9], reinforcement learning (RL) is introduced to enhance the online trading performance.”
BackgroundSpatiotemporal adaptive neural network for long-term forecasting of financial time series
Chatigny, P., Patenaude, J.-M., & Wang, S. (2020) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2020.12.002 · Cited by 24
“Alternatively, RL approaches like [48, 49, 42] can be applied where a model generates trade actions based on their perceived state of their environment.”
BackgroundBiased Pressure: Cyclic Reinforcement Learning Model for Intelligent Traffic Signal Control
Ibrokhimov, B., Kim, Y.-J., & Kang, S.-G. (2022) · Sensors · doi:10.3390/s22072818 · Cited by 21
“In recent years, deep RL has become progressively popular in many machine learning domains and real-world applications, such as robotics [45], finance [46], self-driving cars [47], healthcare [48], smart grids [49], and social networks [50], even beating human performances in some domains.”
BackgroundStochastic Neural Networks-Based Algorithmic Trading for the Cryptocurrency Market
Kalariya, V., Parmar, P., Patel, J., Tanwar, S., Raboacă, M. S., Alqahtani, F. H., Tolba, A. K. R., & Neagu, B.-C. (2022) · Mathematics · doi:10.3390/math10091456 · Cited by 21
Stock Portfolio Management by Using Fuzzy Ensemble Deep Reinforcement Learning Algorithm
Hao, Z., Zhang, H., & Zhang, Y. (2023) · Journal of risk and financial management · doi:10.3390/jrfm16030201 · Cited by 29
Cornalba, F., Disselkamp, C., Scassola, D., & Helf, C. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09033-7 · Cited by 27
“For actor-based methods, we mention recurrent reinforcement learning baselines [43, 44], multilayered risk management systems [45], and high-level feature extraction [46, 47].”
MethodA preliminary study on deep learning for predicting social insurance payment behavior
Ying, J. J.-C., Huang, P., Chang, C., & Yang, D. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258131 · Cited by 17
“While sequence-to-sequence prediction model learning have been developed for dealing with many kinds of sequential data, such as Financial Data Analysis [3], Speech Signal Processing [6] [8] [17] [24], and Natural Language Processing [23], the problem has not been well explored under the context of pension insurance p…”
BackgroundMitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise
Behzadan, V., & Munir, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-99229-7_34 · Cited by 28
Direct Cellularity Estimation on Breast Cancer Histopathology Images Using Transfer Learning
Pei, Z., Cao, S., Lu, L., & Chen, W. (2019) · Computational and Mathematical Methods in Medicine · doi:10.1155/2019/3041250 · Cited by 19
“Deep learning methods are generally based on convolutional neural networks (CNNs) that learn features and prediction models with fewer human interventions than conventional machine learning and are also combined with fuzzy learning for robust feature representation [20] and reinforcement learning for self-taught decis…”
Intelligent Trainer for Dyna-Style Model-Based Deep Reinforcement Learning
Dong, L., Li, Y., Zhou, X., Wen, Y., & Guan, K. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3008249 · Cited by 22
“For example, in [35], a DRL agent is proposed to solve financial trading tasks; in [36], a neural RL agent is trained to mimic the human motor skill learning; in [23], an off-policy RL method is proposed to solve nonlinear and nonzero-sum games.”
MethodUltrafast Active Response Strategy against Malfunction Attack on Fault Current Limiter
Wei, F., Wan, Z., He, H., & Lin, X. (2019) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2019.2960459 · Cited by 17
“A recurrent deep neural network is adopted in [21] to realize real-time financial signal representation and trading.”
BackgroundSynthetic Data Augmentation for Deep Reinforcement Learning in Financial Trading
Liu, C., Ventre, C., & Polukarov, M. (2022) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3533271.3561704 · Cited by 26
“Advanced DRL algorithms can be categorized into three types: value-based algorithms [5, 6, 11], policy-based algorithms [7, 12, 21] and actor-critic based algorithms”
MethodA Portfolio Model with Risk Control Policy Based on Deep Reinforcement Learning
Jiang, C., & Wang, J. (2022) · Mathematics · doi:10.3390/math11010019 · Cited by 25
Shrinkage estimation with reinforcement learning of large variance matrices for portfolio selection
Mattera, G., & Mattera, R. (2023) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2023.200181 · Cited by 16
Artificial Intelligence for Financial Services
Kaswan, K. S., Dhatterwal, J. S., Kumar, N., & Lal, S. (2023) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-80455-562-020231006 · Cited by 18
An Intelligent Security System Using Enhanced Anomaly-Based Detection Scheme
Louati, F., Ktata, F. B., & Amous, I. (2024) · The Computer Journal · doi:10.1093/comjnl/bxae008 · Cited by 18
A Multifaceted Approach to Stock Market Trading Using Reinforcement Learning
Ansari, Y., Gillani, S. A., Bukhari, M., Lee, B., Maqsood, M., & Rho, S. (2024) · IEEE Access · doi:10.1109/access.2024.3418510 · Cited by 23
“Nevertheless, these rules-based methods show poor generalization and their performance is usually good in specific market situations [11].”
BackgroundHuman-in-the-Loop Low-Shot Learning
Wan, S., Hou, Y., Bao, F., Ren, Z., Dong, Y., Dai, Q., & Deng, Y. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3011559 · Cited by 22
Self-citationDesign and Application of Intelligent Financial Accounting Model Based on Knowledge Graph
Hou, X. (2022) · Mobile Information Systems · doi:10.1155/2022/8353937 · Cited by 22
“[17] proposed a fuzzy deep direct reinforcement learning deep network for stock price forecasting and trading signal generation.”
BackgroundMemristive Fuzzy Deep Learning Systems
Zhang, Y., Cui, M., Shen, L., & Zeng, Z. (2020) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2020.2995966 · Cited by 17
Data Science Technologies in Economics and Finance: A Gentle Walk-In
Barbaglia, L., Consoli, S., Manzan, S., Recupero, D. R., Saisana, M., & Pezzoli, L. T. (2021) · Springer eBooks · doi:10.1007/978-3-030-66891-4_1 · Cited by 26
Kabir, M. M., Lima, A. A., Mridha, M. F., Hamid, M. A., & Monowar, M. M. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-6636-0_23 · Cited by 16
Deep Reinforcement Learning based Adaptive Real-Time Path Planning for UAV
Li, J., & Yang, L. (2021) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/dsa52907.2021.00077 · Cited by 15
“Deep Reinforcement Learning (DRL), integrating the powerful perception and representation ability of deep neural network to deal with high-dimensional decision information and the learning ability for decision-making of reinforcement learning through trial-and-error, has been applied in [7], [8].”
BackgroundDeep differentiable reinforcement learning and optimal trading
Jaisson, T. (2022) · Quantitative Finance · doi:10.1080/14697688.2022.2062431 · Cited by 26
“com not want to spend his alpha in trading costs, see Frazzini et al. (2012). This implies that the current choice of portfolio weights does not only impact the portfolio returns over the next short period but also the future investor positioning.”
BackgroundInfluentialTAG: Teacher-Advice Mechanism With Gaussian Process for Reinforcement Learning
Lin, K., Li, D., Li, Y., Chen, S., Liu, Q., Gao, J., Jin, Y., & Gong, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3262956 · Cited by 18
“Therefore, DRL has been employed in a wide range of scenarios, e.g., games [1], [2], recommender systems [3], [4], [5], robot control [6], [7], autonomous driving [8], and financial trade [9].”
Deep reinforcement learning applied to statistical arbitrage investment strategy on cryptomarket
Vergara, G., & Kristjanpoller, W. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111255 · Cited by 17
A dynamic predictor selection algorithm for predicting stock market movement
Dong, S., Wang, J., Luo, H., Wang, H., & Wu, F. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115836 · Cited by 20
A Novel Anti-Risk Method for Portfolio Trading Using Deep Reinforcement Learning
Han, Y., Liu, J., Tian, D., & Zhang, Q. (2022) · Electronics · doi:10.3390/electronics11091506 · Cited by 19
Multi-Asset Spot and Option Market SimulationPreprint
Wiese, M., Wood, B., Pachoud, A., Korn, R., Buehler, H., Murray, P., & Bai, L. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3980817 · Cited by 17
Hu, K., Yao, X., & Qiao, F. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104235 · Cited by 20
Advancing autonomy through lifelong learning: a survey of autonomous intelligent systems
Zhu, D., Bu, Q., Zhu, Z., Zhang, Y., & Wang, Z. (2024) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2024.1385778 · Cited by 27
Relevant Experiences in Replay Buffer
Dao, G., & Lee, M. (2019) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci44817.2019.9002745 · Cited by 15
“There are a lot of methods have been built to solve world challenging problems such as robotics [3], allocating cloud computing resource [12], advertisement technology [21], and finance [5].”
MethodSentiment Aware Stock Price Forecasting using an SA-RNN-LBL Learning Model
Gurav, U., & Kotrappa, S. (2020) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.3805 · Cited by 15
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.