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 101–200 of 822
A novel training algorithm for convolutional neural network
Anuse, A. D., & Vyas, V. (2016) · Complex & Intelligent Systems · doi:10.1007/s40747-016-0024-6 · Cited by 63
“Financial signal representation is done in [71] using deep neural networks.”
BackgroundHirchoua, B., Ouhbi, B., & Frikh, B. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114553 · Cited by 78
Multimodal Agent AI: A Survey of Recent Advances and Future Directions
Sun, Y., Sun, H., Ma, J., Zhang, P., & Huang, X. (2025) · Journal of Computer Science and Technology · doi:10.1007/s11390-025-4802-8 · Cited by 79
Recent Advances in Reinforcement Learning in FinancePreprint
Hambly, B. M., Xu, R., & Yang, H. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3971071 · Cited by 104
Relation-Aware Transformer for Portfolio Policy Learning
Xu, K., Zhang, Y., Ye, D., Zhao, P., & Tan, M. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/641 · Cited by 99
“This can lead to unsatisfactory PS performance due to limited feature representations [Deng and others, 2016].”
Residential Energy Management with Deep Reinforcement Learning
Wan, Z., Li, H., & He, H. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489210 · Cited by 60
“Deep reinforcement learning (RL), combinatin of DNN and RL, has obtained significant success in complex decision-making processes [18]–[23].”
BackgroundShang, P., Liu, X., Yu, C., Yan, G., Xiang, Q., & Mi, X. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103419 · Cited by 63
Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization
Yu, P., Sern, L. J., Kulyatin, I., Shi, Z., & Dasgupta, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08740 · Cited by 58
“In particular, the approaches in (Moody & Saffell, 2001; Dempster & Leemans, 2006; Cumming et al., 2015; Deng et al., 2017) only yield discrete single-asset trading signals.”
MethodTan, J., Liu, H., Li, Y., Yin, S. W., & Yu, C. (2022) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2022.112405 · Cited by 59
Le, T. P., Vien, N. A., & Chung, T. (2018) · IEEE Access · doi:10.1109/access.2018.2854283 · Cited by 75
“RL has been applied to robotics [2]–[5], economics [6]–[8], computer games [9]–[11] and other applications [12]–[14].”
MethodStock Price Prediction by Deep Neural Generative Model of News Articles
Matsubara, T., Akita, R. M., & Uehara, K. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2016iip0016 · Cited by 60
“A market simulation considering commissions and time lags inherent in trading is also future work [30].”
BackgroundIndividualized Indicator for All: Stock-wise Technical Indicator Optimization with Stock Embedding
Li, Z., Yang, D., Zhao, L., Bian, J., Qin, T., & Liu, T. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330833 · Cited by 87
“[7] introduced the contemporary deep learning into a deep reinforcement network for financial signal processing and on-line”
BackgroundMulti-type data fusion framework based on deep reinforcement learning for algorithmic trading
Liu, P., Zhang, Y., Bao, F., Yao, X., & Zhang, C. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03321-w · Cited by 61
Self-citationArtificial intelligence applications in finance: a survey
Li, X., Sigov, A., Ratkin, L., Ivanov, L. A., & Li, L. (2023) · Journal of Management Analytics · doi:10.1080/23270012.2023.2244503 · Cited by 97
Jarosiński, M., Beekman, F., Bada, G., & Cloetingh, S. A. P. L. (2006) · Geophysical Journal International · doi:10.1111/j.1365-246x.2006.02979.x · Cited by 64
Reinforcement Learning in Stock Trading
Dang, Q.-V. (2020) · Advances in Intelligent Systems and Computing · doi:10.1007/978-3-030-38364-0_28 · Cited by 57
“Several research works in using reinforcement learning have been presented [22, 6, 1] in literature.”
BackgroundMethodvrAIn: Deep Learning based Orchestration for Computing and Radio Resources in vRANs
Ayala‐Romero, J. A., García‐Saavedra, A., Gramaglia, M., Costa‐Pérez, X., Banchs, A., & Alcaraz, J. J. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3043100 · Cited by 58
“This falls naturally into the realm of reinforcement learning (RL) [20], an area of machine learning applied in human-level control (mastering games such as Go [21] or StarCraft II [22]), health-care [23] or finances [24].”
BackgroundLee, J., Koh, H., & Choe, H. J. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02218-4 · Cited by 60
Deep learning approach to control of prosthetic hands with electromyography signals
Jafarzadeh, M., Hussey, D. C., & Tadesse, Y. T. (2019) · International Symposium on Measurement and Control in Robotics (ISMCR) · doi:10.1109/ismcr47492.2019.8955725 · Cited by 61
“Image segmentation [27], object detection [28], speech recognition [29], natural language processing [30], playing Atari game [31], object manipulation [32], autonomous driving [33], lung disease detection [34], and financial assert trading [35] are some of the examples of the optimization paradigm shift.”
BackgroundA survey of deep learning applications in cryptocurrency
Zhang, J., Cai, K., & Wen, J. (2023) · iScience · doi:10.1016/j.isci.2023.108509 · Cited by 80
“Deng et al. 76 used RNN to process the characteristics of real-time financial signals and tried to build quantitative trading strategies based on structure to beat experienced financial asset traders.”
MethodKarabayir, İ., Akbilgiç, O., & Taş, N. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2979121 · Cited by 57
Stock Price Manipulation Detection using Generative Adversarial Networks
Leangarun, T., Tangamchit, P., & Thajchayapong, S. (2018) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2018.8628777 · Cited by 60
“[19] introduced deep recurrent neural networks (DRNNs) Data Preprocessing”
BackgroundAn Imbalance Fault Detection Algorithm for Variable-Speed Wind Turbines: A Deep Learning Approach
Chen, J., Hu, W., Cao, D., Zhang, B., Huang, Q., Chen, Z., & Blaabjerg, F. (2019) · Energies · doi:10.3390/en12142764 · Cited by 56
“There are some artificial intelligence methods which can deal with the noise problem and with relatively mature technology, such as the auto-encoder [41], variational auto-encoder, stacked denoising auto-encoder [42], etc.”
A Deep Learning Approach to Competing Risks Representation in Peer-to-Peer Lending
Tan, F., Hou, X., Zhang, J., Wei, Z., & Yan, Z. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2870573 · Cited by 57
“Several P2P lending platforms release their load data to the public, which has received much attention from academia [1]–[7].”
FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance
Liu, X.-Y., Yang, H., Chen, Q., Zhang, R., Yang, L., Xiao, B., & Wang, C. (2025) · doi:10.2139/ssrn.3737859 · Cited by 53
“Deng et al. [12] showed that applying deep neural networks profits more.”
A Multi-objective Deep Reinforcement Learning Approach for Stock Index Future’s Intraday Trading
Si, W., Li, J., Ding, P., & Rao, R. (2017) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2017.210 · Cited by 64
A parallel multi-module deep reinforcement learning algorithm for stock trading
Ma, C., Zhang, J., Liu, J., Ji, L., & Gao, F. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.005 · Cited by 63
A Stock Market Trading System Using Deep Neural Network
Yong, B. X., Rahim, M. R. A., & Abdullah, A. S. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-6463-0_31 · Cited by 58
“Experiment has been conducted to test its profitability and performance as a trading system in the stock and commodity market [6].”
Sentiment-influenced trading system based on multimodal deep reinforcement learning
Chen, Y., & Huang, S.-H. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107788 · Cited by 63
Kwon, Y., & Lee, Z. (2023) · Decision Support Systems · doi:10.1016/j.dss.2023.114100 · Cited by 53
Deep Reinforcement Learning for Financial Trading Using Price Trailing
Saitas-Zarkias, K., Passalis, N., Tsantekidis, A., & Tefas, A. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683161 · Cited by 52
Multiagent-based deep reinforcement learning for risk-shifting portfolio management
Lin, Y.-C., Chen, C.-T., Sang, C.-Y., & Huang, S.-H. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108894 · Cited by 64
Diversity-driven knowledge distillation for financial trading using Deep Reinforcement Learning
Tsantekidis, A., Passalis, N., & Tefas, A. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.02.026 · Cited by 51
A Novel Optimization Algorithm: Cascaded Adaptive Neuro-Fuzzy Inference System
Rathnayake, N., Dang, T. L., & Hoshino, Y. (2021) · International Journal of Fuzzy Systems · doi:10.1007/s40815-021-01076-z · Cited by 46
“Some researches that have been performed to reconstruct the input features using fuzzy sets to reduce the influence of uncertainties [46].”
BackgroundIntelligent Algorithmic Trading Strategy Using Reinforcement Learning and Directional Change
Aloud, M., & Alkhamees, N. (2021) · IEEE Access · doi:10.1109/access.2021.3105259 · Cited by 39
“…in financial and machine learning literature have exploited RL in different financial market studies, e.g., financial signal representation [4], [7], [14], building algorithmic trading [4], [8]–[10], [15], [16], portfolio management [11], [17], [18], optimizing trade execution [19], Foreign Exchange…”
BackgroundAlshahrani, S., Khan, K., Abido, M. A., & Khalid, M. (2023) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-023-08399-z · Cited by 57
“The DRL is a derivative method that combines the deep learning with the reinforcement learning that excelled in games [274], natural language processing [275], robotics [276], finance and business management [277].”
Estimating the impact of domain-specific news sentiment on financial assets
Kelly, S., & Ahmad, K. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.03.004 · Cited by 55
FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance
Liu, X.-Y., Yang, H., Gao, J., & Wang, C. (2021) · doi:10.2139/ssrn.3955949 · Cited by 46
Kuo, C.-H., Chen, C.-T., Lin, S.-J., & Huang, S.-H. (2021) · IEEE Access · doi:10.1109/access.2021.3068269 · Cited by 59
“…with RL to achieve impressive performance in several domains of finance, such as forex The associate editor coordinating the review of this manuscript and approving it for publication was Constantinos Marios Angelopoulos . trading [6], portfolio management [4], [5], [7], [8], and market making [9].”
BackgroundAlphaPortfolio for Investment and Economically Interpretable AIPreprint
Cong, L. W., Tang, K., Wang, J., & Zhang, Y. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3554486 · Cited by 58
A Robust Handwritten Numeral Recognition Using Hybrid Orthogonal Polynomials and Moments
Abdulhussain, S. H., Mahmmod, B. M., Naser, M. A., Alsabah, M. Q., Ali, R., & Al-Haddad, S. A. R. (2021) · Sensors · doi:10.3390/s21061999 · Cited by 44
Adversarial Active Learning for Sequences Labeling and Generation
Deng, Y. C., Chen, K., Shen, Y., & Jin, H. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/558 · Cited by 40
Self-citationDing, F., & Luo, C. (2020) · IEEE Access · doi:10.1109/access.2020.2982662 · Cited by 52
“Deng et al. [28] proposed a trading system based on fuzzy deep direct reinforcement (FDDR), which applied the fuzzy learning to the denoising of the price.”
BackgroundMethodInfluentialStock Trading Strategies Based on Deep Reinforcement Learning
Li, Y., Liu, P., & Wang, Z. (2022) · Scientific Programming · doi:10.1155/2022/4698656 · Cited by 60
“[33] proposed a model Deep Direct Reinforcement Learning and added fuzzy learning, which is the first attempt to combine deep learning and reinforcement learning in the field of financial transactions.”
MethodGPM: A graph convolutional network based reinforcement learning framework for portfolio management
Shi, S., Li, J., Li, G., Pan, P., Chen, Q., & Sun, Q. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.105 · Cited by 46
Wu, D., Wang, X., & Wu, S. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118006 · Cited by 47
Sentiment and Knowledge Based Algorithmic Trading with Deep Reinforcement Learning
Nan, A., Perumal, A., & Zai͏̈ane, O. R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-12423-5_13 · Cited by 54
Deep Reinforcement Learning in Agent Based Financial Market Simulation
Maeda, I., deGraw, D., Kitano, M., Matsushima, H., Sakaji, H., Izumi, K., & Kato, A. (2020) · Journal of risk and financial management · doi:10.3390/jrfm13040071 · Cited by 56
“Various types of deep reinforcement learning methods are used in financial applications depending on the task (Deng et al. 2016; Jiang and Liang 2017; Jiang et al. 2017).”
Tea yield estimation using UAV images and deep learning
Wang, S., Yu, C., JunHui, M., Ouyang, J.-X., Zhao, Z.-M., Xuan, Y., Fan, D., Yu, J., Wang, X., & Zheng, X. (2024) · Industrial Crops and Products · doi:10.1016/j.indcrop.2024.118358 · Cited by 40
Continuous-time reinforcement learning approach for portfolio management with time penalization
García-Galicia, M., Carsteanu, A. A., & Clempner, J. B. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.03.055 · Cited by 37
Alonso, R. S., Sittón-Candanedo, I., Vara, R. C., Prieto, J., & Corchado, J. M. (2020) · Sustainability · doi:10.3390/su12145706 · Cited by 40
“Among its applications are self-driving cars [59], robot vacuums [60], automated trading [61], enterprise resource management [62,63] or games.”
BackgroundShang, W., Chen, Y., Li, X., & Ochieng, W. Y. (2020) · Complexity · doi:10.1155/2020/8841317 · Cited by 46
“DRL is able to handle complicated tasks with lower prior knowledge, even in high-dimensional space [40]; therefore, it has many potential applications in real world, such as robotics [42], autonomous driving [43], and economics [44].”
BackgroundA new metric for individual stock trend prediction
Liu, G., & Wang, X. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.03.019 · Cited by 38
Kesse, M. A., Buah, E., Handroos, H., & Ayetor, G. K. (2020) · Metals · doi:10.3390/met10040451 · Cited by 39
A synchronous deep reinforcement learning model for automated multi-stock trading
Kawy, R. A., Abdelmoez, W., & Shoukry, A. (2021) · Progress in Artificial Intelligence · doi:10.1007/s13748-020-00225-z · Cited by 49
What is the Value of the Cross-Sectional Approach to Deep Reinforcement Learning?
Aboussalah, A. M., Xu, Z., & Lee, C.-G. (2020) · Quantitative Finance · doi:10.1080/14697688.2021.2001032 · Cited by 51
“(Deng et al. 2017) proposed a task-aware scheme to manage the vanishing/exploding gradient in recurrent RL.”
Dynamic stock-decision ensemble strategy based on deep reinforcement learning
Yu, X., Wu, W., Liao, X., & Han, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03606-0 · Cited by 49
“Therefore, reinforcement learning seems to be a very good choice for learning optimal stock trading strategies [15].”
BackgroundSparse Index Tracking With K-Sparsity or ϵ-Deviation Constraint via ℓ 0 -Norm Minimization
Li, X. P., Shi, Z.-L., Leung, C.-S., & So, H. C. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3171819 · Cited by 36
“In addition, a deep neural network approach [8] was proposed to handle trading decisions for improving rewards in an unknown market environment.”
BackgroundAsset correlation based deep reinforcement learning for the portfolio selection
Zhao, T., Ma, X., Li, X., & Zhang, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119707 · Cited by 48
Cherrat, E. A., Raj, S., Kerenidis, I., Shekhar, A., Wood, B., Dee, J., Chakrabarti, S., Chen, R., Herman, D., Hu, S., et al. (2023) · Quantum · doi:10.22331/q-2023-11-29-1191 · Cited by 71
“At the same time, machine learning has been identified as one of the most important domains of applicability of quantum computing given the potential ability of quantum computers to solve classically-intractable computational problems [9], perform linear algebraic operations efficiently [10] and…”
BackgroundThe Evolution of Reinforcement Learning in Quantitative Finance: A Survey
Pippas, N., Ludvig, E. A., & Turkay, Ç. (2025) · ACM Computing Surveys · doi:10.1145/3733714 · Cited by 71
High-performance stock index trading via neural networks and trees
Chalvatzis, C., & Hristu‐Varsakelis, D. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106567 · Cited by 42
Felizardo, L., Paiva, F. C. L., Graves, C. D. V., Matsumoto, É. Y., Costa, A. H. R., Del-Moral-Hernandez, E., & Brandimarte, P. (2022) · Expert systems with applications · doi:10.1016/j.eswa.2022.117259 · Cited by 30
Deep hedging of long-term financial derivatives
Carbonneau, A. (2021) · Insurance Mathematics and Economics · doi:10.1016/j.insmatheco.2021.03.017 · Cited by 41
“RL has been applied successfully in many areas of quantitative finance such as algorithmic trading (e.g. Moody and Saffell (2001) and Deng et al. (2016)), portfolio optimization (e.g. Jiang et al. (2017) and Almahdi and Yang (2017)) and option pricing (e.g. Li et al. (2009), Becker et al. (2019) and…”
MethodBeating the Stock Market with a Deep Reinforcement Learning Day Trading System
Martinez, L. C., & Pereira, A. C. M. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206938 · Cited by 38
“For instance, [21] [26] [33] [34] are some of the previous model-free successful attempts to tackle alpha generation problems without predicting future prices, but these RL algorithms are limited to single-asset and do not apply to general asset allocation problems.”
BackgroundStock Market Prediction-by-Prediction Based on Autoencoder Long Short-Term Memory Networks
Faraz, M., Khaloozadeh, H., & Abbasi, M. (2020) · Iranian Conference on Electrical Engineering · doi:10.1109/icee50131.2020.9261055 · Cited by 34
“Recurrent neural networks (RNNs) [7], LSTMs [8], deep belief networks (DBNs) [9], and reinforcement learning (RL) [10] methods are also used in stock price prediction.”
MethodMCI-GRU: Stock prediction model based on multi-head cross-attention and improved GRU
Zhu, P. F., Li, Y., Hu, Y., Xiang, S., Liu, Q., Cheng, D., & Liang, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130168 · Cited by 52
“Common value-based approaches in investment strategies include Q-learning [46], Deep Q-learning [47, 48], Recurrent Reinforcement Learning [49, 50], and Sarsa [51, 52].”
Using Reinforcement Learning in the Algorithmic Trading Problem
Ponomarev, E. S., Oseledets, I. V., & Cichocki, A. S. (2019) · Journal of Communications Technology and Electronics · doi:10.1134/s1064226919120131 · Cited by 44
Huang, S.-H., Miao, Y.-H., & Hsiao, Y.-T. (2021) · IEEE Access · doi:10.1109/access.2021.3082186 · Cited by 40
“[2] have applied the model-free method”
Structural break-aware pairs trading strategy using deep reinforcement learning
Lu, J.-Y., Lai, H.-C., Shih, W.-Y., Chen, Y.-F., Huang, S.-H., Chang, H., Wang, J.-Z., Huang, J., & Dai, T. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-04013-x · Cited by 39
“While none of the previous methods [24, 30, 50] considers the hold action, we make the first attempt to adopt it in SADQN for the aforementioned advantages.”
BackgroundMethodInfluentialQiu, Y., Liu, R., & Lee, R. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122243 · Cited by 44
Dreaming machine learning: Lipschitz extensions for reinforcement learning on financial markets
Calabuig, J. M., Falciani, H., & Sánchez-Pérez, E. A. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.052 · Cited by 37
Learning Deep Landmarks for Imbalanced Classification
Bao, F., Deng, Y. C., Kong, Y., Ren, Z., Suo, J., & Dai, Q. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2927647 · Cited by 37
“Compared with shallow learning, deep learning shows the ability to learn hierarchical feature representations by mimicking the supervised labels [11], [12].”
BackgroundSelf-citationSurvey on the application of deep learning in algorithmic trading
Wang, Y., & Yan, G. (2021) · Data Science in Finance and Economics · doi:10.3934/dsfe.2021019 · Cited by 40
“Deng et al. (2017) combined DNN with RL to build a new learning framework. In this framework, the DNN part automatically perceives dynamic market conditions for information feature learning, and then the RL part interacts with the DNN and makes transaction decisions to accumulate final rewards in an unknown environmen…”
Sun, S., Xue, W., Wang, R., He, X., Zhu, J., Li, J., & An, B. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557283 · Cited by 58
“However, traditional finance methods are not perceptive enough to capture fleeting intraday patterns and only perform well in certain market conditions [7].”
BackgroundMethodInfluentialDelay-Optimal Traffic Engineering through Multi-agent Reinforcement Learning
Pinyoanuntapong, P., Lee, M., & Wang, P. (2019) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infcomw.2019.8845154 · Cited by 34
“Recent advances in reinforcement learning (RL) have provided diverse solutions to complex problems such as robotics [6], [7], cloud computing [8], [9], advertisement [10], and finance [11].”
BackgroundNew challenges in reinforcement learning: a survey of security and privacy
Lei, Y., Ye, D., Shen, S., Sui, Y., Zhu, T., & Zhou, W. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10348-5 · Cited by 39
“2016), finance (Deng et al. 2016), selfdriving cars (Pan et al.”
BackgroundDeep Reinforcement Learning Model for Stock Portfolio Management Based on Data Fusion
Li, H., Wu, R., & Hai, M. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11582-4 · Cited by 46
“Features Evaluations FRDNN[17] Combine deep learning and fuzzy learning to strengthen the information feature extraction ability of RRL Experiments in the futures market showed that FRDNN returns were better than RRL and DNN EIIE [18] 1.”
Pre-training with non-expert human demonstration for deep reinforcement learning
de la Cruz, G. V., Du, Y., & Taylor, M. E. (2019) · The Knowledge Engineering Review · doi:10.1017/s0269888919000055 · Cited by 39
“This drawback has made deep RL impractical in real-world applications where data is expensive to collect, such as in robotics, self-driving cars, finance, or medical applications (Bojarski et al. 2017, Deng et al. 2017, Miotto et al. 2017).”
Predictive Analysis of Cryptocurrency Price Using Deep Learning
Yao, Y., Yi, J., Zhai, S., Lin, Y., Kim, T., Zhang, G., & Lee, L. Y. (2018) · International Journal of Engineering & Technology · doi:10.14419/ijet.v7i3.27.17889 · Cited by 35
“Deng et al. [14] proposed a deep direct reinforcement learning framework for financial signal representation and trading.”
BackgroundGenetic Algorithm-Optimized Fuzzy Lyapunov Reinforcement Learning for Nonlinear Systems
Kukker, A., & Sharma, R. (2019) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-019-04126-9 · Cited by 33
Deep deterministic portfolio optimization
Chaouki, A., Hardiman, S. J., Schmidt, C., Serié, E., & de Lataillade, J. (2020) · The Journal of Finance and Data Science · doi:10.1016/j.jfds.2020.06.002 · Cited by 41
A Review of Reinforcement Learning in Financial Applications
Bai, Y., Gao, Y., Wan, R., Zhang, S., & Song, R. (2024) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-112723-034423 · Cited by 84
Deep and Structured Robust Information Theoretic Learning for Image Analysis
Deng, Y. C., Bao, F., Deng, X., Wang, R., Kong, Y., & Dai, Q. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2588330 · Cited by 32
Self-citationAn adaptive mechanism to achieve learning rate dynamically
Zhang, J., Hu, F., Li, L., Xu, X., Yang, Z., & Chen, Y. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3495-0 · Cited by 35
“Those models can also be applied to many neural network problems, such as the fuzzy neural network [49] or recurrent neural networks [50].”
BackgroundA Hybrid Recursive Implementation of Broad Learning With Incremental Features
Liu, D., Baldi, S., Yu, W., & Chen, C. L. P. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3043110 · Cited by 30
“finance and trading [18], and many other domains.”
BackgroundDang, Q., Xu, W., & Yuan, Y. (2022) · Machine Intelligence Research · doi:10.1007/s11633-022-1314-7 · Cited by 30
“Over the last decades, RL algorithm has been applied in diverse fields, such as computer vision[42], financial investment[43], automatic driving[44], natural language processing[45], robot control[46], and building energy[47].”
MethodA Deep Reinforcement Learning Based Real-Time Solution Policy for the Traveling Salesman Problem
Ling, Z., Zhang, Y., & Chen, X. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3256563 · Cited by 35
“With the powerful fitting capabilities of DNNs, the DRL has been extended to tackle complex dynamic modeling and optimization processes in finance [14], traffic [15], and agriculture [16].”
Data selection to avoid overfitting for foreign exchange intraday trading with machine learning
Peng, Y.-L., & Lee, W. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107461 · Cited by 33
Passalis, N., Avramelou, L., Seficha, S., Tsantekidis, A., Doropoulos, S., Makris, G., & Tefas, A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07509-6 · Cited by 36
“Several different approaches have been proposed in the literature for training DL models for financial trading, ranging from classification-based methods [29] to complex reinforcement learning setups which aim to simulate the trading environment [10].”
BackgroundMethodKwak, D., Choi, S., & Chang, W. (2022) · Information Sciences · doi:10.1016/j.ins.2022.12.042 · Cited by 30
Q‐RTS: a real‐time swarm intelligence based on multi‐agent Q‐learning
Matta, M., Cardarilli, G. C., Nunzio, L. D., Fazzolari, R., Giardino, D., Re, M., Silvestri, F., & Spanò, S. (2019) · Electronics Letters · doi:10.1049/el.2019.0244 · Cited by 29
Gaussian Weighting Reversion Strategy for Accurate Online Portfolio Selection
Cai, X., & Ye, Z. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2941067 · Cited by 29
“[32].”
Zhang, L., Wu, X., Zhao, H., Cheng, F., & Liu, Q. (2020) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2020.2993446 · Cited by 29
An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms
Shan, C., Mamoulis, N., Cheng, R. C. K., Li, G., Li, X., & Qian, Y. (2020) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde48307.2020.00012 · Cited by 30
“Deep RL has experienced dramatic growth recently in multiple fields, such as games (AlphaGo) [20], [28], [30], robotics [9], natural language processing [21], computer vision [18], finance [7], computer systems [16], [19], [36] and recommender systems [37], [38].”
Combining Artificial Immune System and Clustering Analysis: A Stock Market Anomaly Detection Model
Close, L., & Kashef, R. F. (2020) · Journal of Intelligent Learning Systems and Applications · doi:10.4236/jilsa.2020.124005 · Cited by 28
“AIS is applied to real-time traffic monitoring systems in [22], where once again, it shows promise in being more stable and efficient than the leading methods.”
MethodZhang, C., Li, Y., Chen, X., Jin, Y., Tang, P., & Li, J. (2020) · Proceedings · doi:10.1109/icdm50108.2020.00087 · Cited by 29
Sun, R., Jiang, Z., & Su, J. (2021) · IEEE International Conference on Big Data Analytics (ICBDA) · doi:10.1109/icbda51983.2021.9403210 · Cited by 31
“Inspired by the outstanding performance of RL algorithm in the field of video game [4] and board games [5], scholars try to adopt the reinforcement learning algorithm in the field of finance [28], [29].”
MethodDeep Reinforcement Learning in Quantitative Algorithmic Trading: A ReviewPreprint
Pricope, T.-V. (2021) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2106.00123 · Cited by 104
“We will briefly mention Deep Reinforcement Learning for Trading [19] as well, though their experiments focus on futures contracts and not stocks.”
InfluentialEvolution-Guided Adaptive Dynamic Programming for Nonlinear Optimal Control
Wang, D., Huang, H., Liu, D., Zhao, M., & Qiao, J. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3417230 · Cited by 28
“These challenges encompass the issue of gradient vanishing [6] and the absence of effective exploration [7].”
Background
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.