Deep reinforcement learning for automated stock trading: an ensemble strategy
The DOI matches its Crossref record, with a small difference in title or year; 47 of the 47 references it cites were found in a registry or an index.
Abstract
Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market situations. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand technique for processing very large data. We test our algorithms on the 30 Dow Jones stocks that have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble strategy is shown to outperform the three individual algorithms and two baselines in terms of the risk-adjusted return measured by the Sharpe ratio.
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
“Deep reinforcement learning (DRL), that balances exploration (of uncharted territory) and exploitation (of current knowledge), is a promising approach to automate trading in quantitative finance [50][51][47][54][21][13].”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [51]
In the citing paper
“Therefore, the backtesting performance demonstrates that FinRL successfully reproduces the ensemble strategy [51].”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [51]
In the citing paper
“The ensemble strategy [51] combines three DRL algorithms (PPO [42], A2C [32] and DDPG [26]) to improve the robustness.”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [51]
In the citing paper
“Explainable DRL for portfolio management [17] and DRL ensemble strategy for stock trading [50, 51] are also implemented.”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [51]
In the citing paper
“The performance in terms of multiple metrics is consistent with the results reported in [51] and [50], and here we show results in a recent trading period.”
From FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance (2021) · cites this paper as [51]
7 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782 · cited 12×
“DDPG performs similar but not as good as PPO, it can be used as a complementary strategy to PPO in a bullish market.”
InfluentialProximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 3×
“The three actor-critic algorithms [24] are Proximal Policy Optimization (PPO) [28, 37], Advantage Actor Critic (A2C) [32, 48], and Deep Deterministic Policy Gradient (DDPG) [28, 29, 44].”
BackgroundMethod(1995) · Cited by 10,558
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 2×
“A2C [32] is a typical actor-critic algorithm and we use it a component in the ensemble strategy.”
BackgroundMethodMarkowitz, H. (1952) · The Journal of Finance · doi:10.1111/j.1540-6261.1952.tb01525.x · Cited by 5,641
(1999) · Cited by 5,147
Sharpe, W. F. (1994) · The Journal of Portfolio Management · doi:10.3905/jpm.1994.409501 · Cited by 2,534
Konda, V. R., & Tsitsiklis, J. N. (2002) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 2,220
International Journal of Economics and Financial Issues
(2021) · International Journal of Economics and Financial Issues · doi:10.32479/ijefi · Cited by 2,008
Research works printed but not linked: 4
- Zhipeng Liang , Kangkang Jiang , Hao Chen , Junhao Zhu , and Yanran Li. 2018. Adversarial deep reinforcement learning in portfolio management. arXiv: Portfolio Management ( 2018 ). Zhipeng Liang, Kangkang Jiang, Hao Chen, Junhao Zhu, and Yanran Li. 2018. Adversarial deep reinforcement learning in portfolio management. arXiv: Portfolio Management (2018).
- John Schulman , Sergey Levine , Philipp Moritz , Michael Jordan , and Pieter Abbeel . 2015 . Trust region policy optimization . In The 31st International Conference on Machine Learning. John Schulman, Sergey Levine, Philipp Moritz, Michael Jordan, and Pieter Abbeel. 2015. Trust region policy optimization. In The 31st International Conference on Machine Learning.
- 10.5555/551283 · doi:10.5555/551283
- Zihao Zhang . 2019. Deep reinforcement learning for trading. ArXiv 2019 (11 2019 ). Zihao Zhang. 2019. Deep reinforcement learning for trading. ArXiv 2019 (11 2019).
Cited by
Items 101–198 of 198
Li, J., Liu, B., Zhou, W., Zhang, T., Duan, X., Ma, N., & Wang, Y. (2025) · Symmetry · doi:10.3390/sym17091550 · Cited by 2
Explaining Neural Networks: Hierarchical Backpropagated Ensemble Learning
He, G., Wang, Z., Tang, L., Zhang, R., Wang, R., Li, X., & Nie, F. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3625434 · Cited by 4
“Convolutional neural networks (CNNs) [25], [26], recurrent neural networks (RNNs) [27], long short-term memory networks (LSTMs) [28], transformers [29], and other models have been incorporated into the Bagging and Boosting Fig.”
Roshanpour, R., Parsanejad, M., & Pishvaee, M. S. (2025) · IEEE Access · doi:10.1109/access.2025.3633234 · Cited by 3
Ultsch, J., Ahmic, K., & Brembeck, J. (2025) · IEEE Access · doi:10.1109/access.2025.3636787 · Cited by 5
“…ids can be shown using tfg get_unevaluated_ids -e residualPFC, which can directly be used in the evaluation command: tfg evaluate -ids [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] -n 10 -e residualPFC The command above starts the evaluation simulations for training ids 1-10 in 10 parallel processes (-n 10).”
Stock Market Intraday Trading Using Reinforcement Learning
Pandit, R. A., Nerkar, N. S., Walunj, P. M., Tank, R. K., & Kolhe, S. R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36402-0_35 · Cited by 2
Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents*
Ataiefard, F., & Hemmati, H. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00099 · Cited by 2
Santos, G. D., & Lima, K. R. (2024) · Anais do Simpósio Brasileiro de Sistemas de Informação (SBSI) · doi:10.1145/3658271.3658282 · Cited by 4
Chen, Y. (2024) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns-2024-2175 · Cited by 2
Chen, H., Xu, C., & Xu, Z. (2024) · Computational Economics · doi:10.1007/s10614-024-10786-z · Cited by 3
“(3) Mitigating potential extreme risks: addressing and mitigating extreme risks is a pivotal challenge in risk management ( Yang et al., 2021).”
Deep Reinforcement Learning for Automated Stock Trading Using Different Reward Schemes
Lawton, S. R., & Jeewa, A. (2024) · IEEE International Conference on Future Machine Learning and Data Science (FMLDS) · doi:10.1109/fmlds63805.2024.00101 · Cited by 3
Deep Q network with action retention for going long and short selling
Sun, Q., & Si, Y. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113252 · Cited by 2
Musaev, J., Anorboev, A., Seo, Y., Fayzullaev, O., Musaev, A., Nguyên, N. T., & Hwang, D. (2025) · IEEE Access · doi:10.1109/access.2025.3593046 · Cited by 2
TradeR: Practical Deep Hierarchical Reinforcement Learning for Trade ExecutionPreprint
Suri, K., Shi, X. Q., Plataniotis, K. N., & Lawryshyn, Y. (2021) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2104.00620 · Cited by 6
“Contrary to pre-existing methods in literature (Yang et al., 2020; Chaouki et al., 2020), we provide the agent with an additional hold action which is equivalent to carrying out no transaction at the given timestep.”
InfluentialPAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization
Ye, Y., Tang, L., Wang, H., Yu, R., Yu, W., He, E., Chen, H., & Xiong, H. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671611 · Cited by 3
“…deep reinforcement learning (DRL) have significantly propelled efforts to optimize sequential decision-making across various fields, including autonomous vehicles [20, 32], treat-ment recommendations [21, 30, 57], and economics [18, 45], extending to industry operation system optimization [16, 25].”
BackgroundEvaluating the Impact of Sentiment Analysis on Deep Reinforcement Learning-Based Trading Strategies
Etcil, M., Kolukısa, B., & Bakır-Güngör, B. (2024) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk63289.2024.10773404 · Cited by 2
Reinforcement Learning in Portfolio Management: A Survey of Methods and Trends
Hu, S., Huang, Y., Agarwal, A., Warrier, T., Yuwen, W., Ma, H., & Luo, Z. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249355 · Cited by 1
Green fees: Sustainability impacts on portfolio management
Alkan, D., Ayari, R., & Paraschiv, F. (2025) · International Review of Financial Analysis · doi:10.1016/j.irfa.2025.104812 · Cited by 1
Ayari, R. (2025) · Quantitative Finance · doi:10.1080/14697688.2025.2592822 · Cited by 2
RiskawareTrader: A Reinforcement Learning based Portfolio Optimization for Risk Averter
Yang, M., Wang, J., & Hu, Y. (2025) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-025-01094-x · Cited by 3
“Values above 70 or below 30 indicate overbought or oversold conditions, respectively, guiding investors to avoid impulsive decisions in extreme market states[ 27 , 28 ].”
Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models
Pokou, F., Kamdem, J. S., & Benhmad, F. (2026) · Computational Economics · doi:10.1007/s10614-025-11191-w · Cited by 2
“This approach refines the prediction by focusing on the most significant market movements.”
Optimizing stock portfolios with deep reinforcement learning after FNN-based fundamental analysis
Sun, Y. J., Lu, Z. Y., Liao, C. H., Dai, T., & Yuan, S. M. (2026) · Quantitative Finance · doi:10.1080/14697688.2025.2604770 · Cited by 1
“To address such risks, we follow Yang et al. (2021) by using the turbulence index (Kritzman and Li 2010) as a risk measurement.”
Khemlichi, F., Khamlichi, Y. I., & Ali, S. E. B. (2026) · Information · doi:10.3390/info17050476 · Cited by 1
Researches advanced in financial trading systems based on reinforcement learning
Zhu, H. (2022) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1117/12.2641867 · Cited by 2
“With the appropriate combination of the actor and critic, the DDPG agent is appropriate for the continuous action space environment such as stock trading [8].”
BackgroundMethodInfluentialResearch on stock trend prediction methods - Taking CSI 300 and CSI 500 as examples
Qiao, Y., Feng, S., & Wu, R.-Z. (2022) · Highlights in Business, Economics and Management · doi:10.54097/hbem.v4i.3535 · Cited by 1
“[6] Therefore, the two original sequences were processed with”
BackgroundEvaluation of Deep Reinforcement Learning Based Stock Trading
Zhang, Y., Zhang, Z., & Yan, H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-24755-2_5 · Cited by 1
Trading Robots: Effective but Limited in Replacing Human Traders for Short-Term Investors
Ady, S. U., Winedar, M., Farida, I., Susena, D. O. S., & Putri, F. M. (2023) · Advances in Social Science, Education and Humanities Research/Advances in social science, education and humanities research · doi:10.2991/978-2-38476-048-0_28 · Cited by 1
Baradja, A., Gernowo, R., & Wibowo, A. (2023) · IEEE International Conference on Smart Technology (ICE-SMARTec) · doi:10.1109/ice-smartech59237.2023.10461955 · Cited by 1
“Another study by [19] and [20] used a combination of A2C and other reinforcement learning algorithms to construct an ensemble strategy that achieved superior performance compared with individual algorithms.”
MethodDeveloping an Investment Method for Securities With Reinforcement Learning
Song, W., Xiong, Z., & Yue, L. (2024) · IEEE Access · doi:10.1109/access.2024.3481245 · Cited by 1
A New DAPO Algorithm for Stock Trading
Zha, R., & Liu, B. (2025) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/ids66066.2025.00013 · Cited by 1
ChronosRL: embeddings-based reinforcement learning agent for financial trading
Lima, A. M. D. A., Oliveira, A. L. I., & Zanchettin, C. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.07.132 · Cited by 1
Deep Hierarchical Reinforcement Learning
Suri, K. (2021) · TSpace (University of Toronto) · Cited by 1
A Deep Reinforcement Learning Approach to Automated Stock Trading, using xLSTM Networks
Sarlakifar, F., Asl, M. M., Khaledi, S. R., & Salimi-Badr, A. (2025) · arXiv · doi:10.48550/arxiv.2503.09655 · Cited by 5
“1) to avoid trading in extreme market situations [9].”
Deep reinforcement learning and signal processing applications for investment strategies
Najar, V. E. (2021) · UPCommons institutional repository (Universitat Politècnica de Catalunya)
Zeng, L., Wang, L., Niu, H., Li, J., Zhang, R., Dai, Z., Zhu, D., & Wang, L. (2021) · arXiv (Cornell University)
SUPPORT SYSTEM FOR SPECULATION BY EXCHANGE TRADES FUNDS
Tumaševičius, G., & Maknickienė, N. (2022) · Mokslas - Lietuvos ateitis · doi:10.3846/mla.2022.15870
Polaris for the Lost in Quantitative Investment
Shao, J., & Yu, Q. (2022) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis54925.2022.9882412
Self-Operating Stock Exchange – A Deep Reinforcement Learning Approach
Mustafa, H. G. (2021) · UMT Artificial Intelligence Review · doi:10.32350/umtair.11.02
Deep Reinforcement Learning for Tehran Stock Trading
Yousefi, N. (2022) · Indonesian Journal of Data and Science · doi:10.56705/ijodas.v3i3.53
Reinforcement Learning for Stock Price Trading with Keywords in Google Trends
You, S. D., Hsiao, P.-Y., & Tsai, S. (2023) · International Conference on Applied System Innovation · doi:10.1109/icasi57738.2023.10179534
“Therefore, this type of algorithm is also suitable for automated stock trading [9,10].”
MethodFinancial Time Series Trading using DDPG Considering Multi-scale Features
Chen, J., Liu, Z., Cai, X., Cai, Z., & Wang, W. (2023) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3594315.3594382
“The existing studies can be divided by the type of algo-rithm used, which include PPO [25, 26], A2C [27], DQN [28, 29], DDPG [30, 31].”
MethodEnsemble Strategy Based on Deep Reinforcement Learning for Portfolio Optimization
Su, X., Zhou, Y., He, S., & Li, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-40292-0_20
Dynamic Asset Allocation Using Trading Agent
You, S. D., Liu, C., & Yen, C.-C. (2023) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan58799.2023.10226821
A-share Trading Strategy Based on MTL-DDPG
Deng, W., Chen, J., Li, Z., Wang, W., & Cai, Z. (2023) · doi:10.1145/3638584.3638600
A novel portfolio strategy approach using deep reinforcement learning
Yang, X., Liu, C., Liu, J., & Yue, H. (2023) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1145/3650215.3650362
“…compare with our portfolio model: the Dow Jones industrial average index (DJI market value), the traditional cyclic reinforcement learning method (RRL), the method based on principal component analysis and wavelet de-agitation (PCA & DWT) [ 11 ] and the SOTA method without index processing [ 12 ] .”
MethodZhong, R. (2023) · International Conference on Big Data, Artificial Intelligence and Risk Management (ICBAR) · doi:10.1145/3656766.3656833
“Yang et al. applied multiple integrated strategies, including averaging, weighted averaging, and nonlinear combination of multiple models, to deep reinforcement learning for automated stock trading, achieving good model performance [10].”
BackgroundAlhusaynan, M. I., & Al‐Mashari, M. (2024) · Journal of Infrastructure Policy and Development · doi:10.24294/jipd.v8i7.4463
Enabling An Informed Contextual Multi-Armed Bandit Framework For Stock Trading With Neuroevolution
Kar, D., Lyu, Z., Ororbia, A. G., Desell, T., & Krutz, D. E. (2024) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3638530.3664145
“No-tably, deep reinforcement learning techniques have been also used to study stock price variations [45, 71, 72].”
Enabling Ensemble Reinforcement Learning with ICN in Mobile Edge Computing Environments
Huang, Y., Kong, B., Feng, W., Mo, C., Liu, H., Yuan, Y., & Cui, L. (2024) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass62177.2024.00063
“H. Yang et al. [22] use three different policy-gradient algorithms to learn stock trading strategies and select the agent with the highest Sharpe ratio to make predictions when choosing actions.”
BackgroundChen, Y., Yan, H., & Ding, Z. (2024) · Research Square · doi:10.21203/rs.3.rs-5340149/v1
Adaptive Risk-Based Control in Financial Trading
Camilleri, M. M., Bajada, J., & Vella, V. (2024) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3677052.3698652 · Cited by 1
Whose Right Is It Anyway? Challenging the Copyright Claim of AI in India
Chakrabarty, S. P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-8457-8_25
Optimizing Foreign Exchange Trading Performance Through Reinforcement Machine Learning Framework
Moung, E. G., Murnizam, H. Y. B., Sufian, M. M., Liaw, V., Farzamnia, A., & Angeline, L. (2024) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke65377.2024.10874712
Deng, D., & Zhu, X. (2024) · International Conference on Computers and Artificial Intelligence Technology (CAIT) · doi:10.1109/cait64506.2024.10963276
Jayakody, I. H., Bandara, M., & Bandaranayake, A. U. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-89813-6_9
Option-Driven Sentiment in FinRL: a PPO Approach to Trading
Li, S., Yu, M., & Dossor, F. (2025) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/ids66066.2025.00020
“We selected PPO due to its well-known stability and ease of implementation [7].”
Comparative Analysis of Reinforcement Learning Algorithms for Decision Making in Algorithmic Trading
Mody, U., Mehta, M., Mody, U., Shah, S., Patel, D., & Kelkar, K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-2179-8_31
Proliferation of SMEs in South Africa: modelling the challenges and outcomes of selling-to-finish
Nkoana, I., & Mashamaite, K. A. (2025) · International Journal of Business Ecosystem and Strategy (2687-2293) · doi:10.36096/ijbes.v7i3.796
“This immediate capital or cash created by “selling - to-finish” strategy are often used to cover other outstanding in the SMEs (Yang, Liu, Zhong & Walid, 2020).”
Pan, W., Zhang, S., Yang, X., Fan, S., Zheng, B., & Gong, Q. (2025) · Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence (DEAI) · doi:10.1145/3745238.3745272
Chen, H., & Xiong, C. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-2838-6.ch006
Chen, H., & Xu, C. (2025) · Group Decision and Negotiation · doi:10.1007/s10726-025-09937-w
“Indicators like custom turbulence measures (Yang et al. 2021) and CoVaR (Pang et al. 2023) are used to quantify systemic risk, although relying on a single indicator is problematic.”
Generalized Fitted Q‐Iteration With Clustered Data
Hu, L., Wang, J., Wu, Z., & Shi, C. (2025) · Stat · doi:10.1002/sta4.70112
“…(Qin et al. 2025; Tang et al. 2019; Xu et al. 2018; Shi, Wang, et al. 2023), real-time bidding (Cai et al. 2017; J. Jin et al. 2018), finance (Carta et al. 2021; X. Liu et al. 2020; Wu et al. 2020; H. Yang et al. 2020) and large language modelling (Ouyang et al. 2022; Shao et al. 2024).”
Minimal shortfall strategies for liquidation of a basket of stocks using reinforcement learning
Pemy, M., & Zhang, N. (2025) · International Journal of Financial Engineering · doi:10.1142/s2424786325500264
Dynamic factor-informed reinforcement learning for enhancing portfolio optimization
Kim, S., Kwon, H., Yoon, J., & Kim, H. Y. (2026) · Financial Innovation · doi:10.1186/s40854-025-00803-x · Cited by 1
“For the Dow Jones dataset, in line with previous studies (Chen et al. 2019, 2021; Yang et al. 2020; Wu et al. 2021; Jang et al. 2023), we partitioned it into a training dataset and a test dataset.”
Lima, A. M. D. A., Oliveira, A. L. I., & Zanchettin, C. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343101
Language Model Orchestrated Financial Agents: An Open-Source Framework
Gundimeda, R. T. (2025) · International Conference for Advancement in Technology (ICONAT) · doi:10.1109/iconat66879.2025.11362528
Dwibedi, T., Devi, N., Rath, S., Panda, M., & Patel, D. K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-95-3486-9_25
Reinforcement Learning for the Development of Trading Strategies with Market-Uncorrelated Returns
Cornejo, T., & Baladron, J. (2025) · International Conference of the Chilean Computer Science Society (SCCC) · doi:10.1109/sccc67219.2025.11420568 · Cited by 1
“DDPG has been successfully applied in financial domains [9], [10], and serves as the foundation for our approach.”
A deep reinforcement learning-based automated stock market trading agent
Darisi, P., Sweetha, S. R., Tharun, V., & Madumidha, S. (2026) · AIP conference proceedings · doi:10.1063/5.0317673
Naren Karthikeyan, B., & Varalakshmi, P. (2026) · International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) · doi:10.1109/icses66558.2026.11478991
“Empirical studies have shown that RL can produce competitive strategies for position sizing and market timing [12], and ensemble designs that combine multiple actor – critic agents can enhance robustness across regimes [13].”
Attention-Driven Deep RL for Portfolio Management: Temporal and Asset-Wise Signals
Su, R., & Wu, S. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0126-6_3
Adversarial Learning for Fraud Detection
Lunghi, D., Simitsis, A., & Bontempi, G. (2026) · Springer eBooks · doi:10.1007/978-3-032-18765-9_11
Akhmedov, F., Cho, Y. I., Sattarov, O., Sodikovich, Y. S., Mallayev, O., Khujamatov, H., & Crăciunescu, R. (2026) · Mathematics · doi:10.3390/math14122075
Trading Policy Optimization Using Deep Reinforcement Learning for the Dhaka Stock Exchange
Nabil, M. R. T., Patwary, F. A., Hussain, E., & Mahbub, M. S. (2026) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain69676.2026.11545904
Nouira, A. Y., & Amara, M. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01175-w · Cited by 1
“A trading algorithm that uses the PPO to create buy or sell choices was suggested by [9] and [20].”
InfluentialÖztürk, C. (2026) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis...1825313
Gu, J., Du, W., Zhao, X., Rahman, A. M. M., & Wang, G. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3701681
Costa, O. Z. D., Dalmazo, B. L., de Mattos, V. L. D., Pinto, R. F., Bruno, D. R., Borges, E. N., Lucca, G., Cardoso, F. C., & Berri, R. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30488-9_34
Deep Reinforcement Learning Framework for Automated Trading Decision Support Systems
Kaur, G., Saini, S., Rani, P., Khan, L., Avthankar, A., & Shelke, N. M. (2026) · International Conference on Connected Intelligence for Industrial Applications (CI2A) · doi:10.1109/ci2a69097.2026.11576883
Gu, F., Zhang, Z., Ren, X., Li, Z., Wang, H., Jiang, Z., Stefanidis, A., García‐Fernández, Á. F., Su, J., & Li, H. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582057
459Chapter 19 Deep Reinforcement Learning in Financial Trading and Management
Arumugam, S. K., Hariharan, R., & Sivarethinamohan, R. (2026) · De Gruyter eBooks · doi:10.1515/9783111633909-019
A Signal-driven Hierarchical Cross-Attention Portfolio Agent with Deep Reinforcement Learning
Gu, F., Ren, X., Jiang, Z., Zhang, Z., Li, Z., Wang, H., Pang, Z., Stefanidis, A., García‐Fernández, Á. F., Su, J., et al. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582012
Zhang, Y., Liu, F., Xu, C., & Luo, M. (2026) · Mathematics · doi:10.3390/math14132437
Rout, A. K., Acharya, U. D., Aithal, P. K., & Sharma, A. (2026) · Discover Computing · doi:10.1007/s10791-026-10336-1 · Cited by 1
AlphaSeek: Trajectory-Level Self-iterative Factor Mining Framework for Multi-source Financial Data
Zhu, Q., Lu, Z., Zhu, J., Chen, N., Yin, S., & Fong, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3400-4_22 · Cited by 2
“…return objectives, but they are prone to fall into local optima in high-dimensional feature space and lack effective overfitting control mechanisms [42, 36]; DL technologies can extract complex nonlinear factor representations, but they face an intractable "black box" problem, where the generated…”
Wensheng, Y. (2026) · WSEAS Transactions on Circuits and Systems archive · doi:10.37394/23201.2026.25.23
Vakili, A., Khojasteh, M. S., Veisi, M., & Salimi-Badr, A. (2026) · International Interdisciplinary Conference on Artificial Intelligence: Engineering, Health, Finance and Humanities (IICAI) · doi:10.1109/iicai70155.2026.11621054
“For example, [6] proposed an ensemble DRL strategy combining Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Deterministic Policy Gradient (DDPG).”
Dynamics of Boltzmannian temporal difference reinforcement learning in social dilemmas
Leonidov, A. V., Titov, A., & Vasilyeva, E. E. (2026) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2026.118875
Iklassov, Z., Madmoun, H., Duhot, J.-J., & Lahlou, S. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3816459
Portfolio Optimization with TD3 Algorithm Using Technical Indicators
Šimon, T., Likavec, P., Čavojský, M., & Drozda, M. (2026) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-032-32104-6_55
A survey on LLM-enhanced reinforcement learning in financial markets
aldaffaie, G. H. J. A., Taheri, A., Farhadi, A., & Zamanifar, A. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02018-0
Intelligent agents: architectures, learning paradigms, deployment models, and applications
Dritsas, E., & Τρίγκα, Μ. (2026) · Evolutionary Intelligence · doi:10.1007/s12065-026-01259-3 · Cited by 2
Ensemble Deep Reinforcement Learning (DRL) for Adaptive Crypto Trading with Risk Control
Lekha, J., & Salim, M. (2026) · International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT) · doi:10.1109/tqcebt67648.2026.11681775
“Yang et al. [4] improved this field by an ensemble of Proximal Policy Optimization (PPO) [6], Advantage Actor-Critic (A2C) [7], and Deep Deterministic Policy Gradient (DDPG) [8] optimizing Dow Jones portfolios with Sharpe ratio of 1.30.”
InfluentialDynamic-Flooding Transformer Ensembles for Reinforcement-Learning-Based Equity Market Timing
Chen, T.-L., & Jang, J. R. (2026) · IEEE Access · doi:10.1109/access.2026.3734627
Sutar, S. G., Jacob, D. G., & Jeyasudha, J. (2026) · International Conference on Natural Language Processing and Computer Vision (ICNPCV) · doi:10.1109/icnpcv69434.2026.11708808
“Furthermore, numerous research endeavours evaluate their models using limited datasets, often without comprehensive out-of-sample validation, which presents concerns related to overfitting and practical utility [5], [7].”
Gu, F., Ren, X., Jiang, Z., García‐Fernández, Á. F., Su, J., & Li, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729708
Trajectory-Guided Weight Adaptation for Ensemble Reinforcement Learning
Stinson, C., Vamplew, P. W., Dazeley, R., Sandoval, E. B., & Cruz, F. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728773
“For example, [18] integrates PPO, A2C, and DDPG in a stock trading environment, cyclically deploying the algorithm with the best Sharpe ratio on a validation period.”
Chavda, R. P., Mansha, M., Kar, P., Khan, A. U., Kar, B., Kumar, A., & Chaudhury, K. S. (2026) · International Conference on Intelligent Computing and Sustainable Innovations in Technology (IC-SIT) · doi:10.1109/ic-sit69723.2026.11735994
“Yang et al. [18] showed that an ensemble of A2C, PPO, and DDPG agents outperforms any individual method.”
Karaca, A., & Tagluk, M. E. (2026) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap71869.2026.11728074
Metadata
- Authors
- Yang, H., Liu, X.-Y., Zhong, S., & Walid, A.
- Affiliations
- Columbia University (US)
- Wormpex AI Research
- Nokia-Bell Labs
- Venue
- Proceedings of the First ACM International Conference on AI in Finance
- Publisher
- ACM
- Published
- 2020-10-15
- Pages
- 1-8
- OpenAlex
- W3203680104
- Cited by
- 196
- References
- 47
- Citations by year
- 2026: 38 · 2025: 40 · 2024: 51 · 2023: 32 · 2022: 24 · 2021: 10 · 2020: 1
- FWCI
- 22.74
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on AI in Finance (ICAIF) (publishedVersion)
- 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
- Social Sciences › Economics, Econometrics and Finance › Finance › Stochastic processes and financial applications
- Keywords
- automated stock trading, deep reinforcement learning, actor-critic algorithms, proximal policy optimization, Advantage Actor-Critic, deep deterministic policy gradient, continuous action spaces, Sharpe ratio
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.