Multi-Agent Reinforcement Learning Based Financial Portfolio Optimization and Risk Prediction System

[1] R. Sharma, A. Mishra, P. Verma, and S. Patel, “Dynamic portfolio optimization with deep reinforcement learning: Empirical insights from Indian capital markets,” J. Financial Data Sci., vol. 8, no. 1, pp. 115–135, 2026. [Online]. Available: https://www.pmresearch.com/content/iijjfds/8/1/115
[2] E. Schmidt, J. Hoffmann, H. Mueller, and K. Weber, “Optimizing stock portfolios with deep reinforcement learning after FNN-based fundamental analysis,” Quant. Finance J., vol. 26, no. 1, pp. 8–31, 2026. [Online]. Available: https://www.ingentaconnect.com/content/routledg/quant/2026/00000026/00000001/art00008
[3] J. Liang, “Machine learning in asset pricing and portfolio management: A comprehensive review,” Ph.D. dissertation, Univ. of Glasgow, 2025. [Online]. Available: https://theses.gla.ac.uk/84858/3/2024liangphd.pdf
[4] A. Li, M. Chen, J. Park, and T. Kim, “MAC: A multi-agent reinforcement learning framework with correctable asset strategies for portfolio management,” in Proc. IEEE Int. Conf. Knowledge Innovation and Invention (ICKII), 2025. [Online]. Available: https://alia0801.github.io/publication/2025-08-22-ickii-mac
[5] M. Ahmed, S. Khan, R. Desai, and J. Kumar, “Risk-adjusted deep reinforcement learning for portfolio optimization: A multi-reward approach,” Appl.
Intell. Mach. Learn., vol. 55, no. 2, pp. 234–256, 2025. [Online]. Available: https://link.springer.com/article/10.1007/s44196-025-00875-8
[6] L. Chen, P. Wu, J. Zhang, and K. Huang, “Dynamic portfolio optimization with data-aware multi-agent reinforcement learning,” Preprints.org, Nov. 2025. [Online]. Available: https://www.preprints.org/manuscript/202511.0447/v1
[7] R. Kumar, S. Patel, M. Gupta, and V. Singh, “Modular reinforcement learning for multi-market portfolio optimization: A comparative study,”
Information, vol. 16, no. 11, pp. 961–982, 2025. [Online]. Available: https://www.mdpi.com/2078-2489/16/11/961
[8] T. Johnson, A. Chen, K. Rodriguez, and L. Martinez, “Regret-optimized portfolio enhancement through deep reinforcement learning and future looking rewards,” arXiv:2502.02619, 2025. [Online]. Available: https://arxiv.org/abs/2502.02619
[9] J. Davis, M. Thompson, L. Anderson, and P. Johnson, “A deep reinforcement learning and predictive architecture for stock portfolio management,” in Proc. CUCAI, 2025, pp. 234–248. [Online]. Available: https://cucai.ca/2025/papers/Ja5VMK
[10] K. Kabir and P. Wang, “Deep reinforcement learning for portfolio management: A relation-aware transformer approach with online adaptation,”
Temple Univ., AI Project Rep., 2025. [Online]. Available: https://cis.temple.edu/~pwang/5603-AI/Project/2025F/Kabir/Report.pdf
[11] Y. Liu, H. Sun, J. Wang, and Q. Zhou, “Portfolio management based on value distribution reinforcement learning algorithms in financial markets,” Front. Artif. Intell., vol. 9, Art. no. 1709493, 2025. [Online]. Available: https://www.frontiersin.org/journals/artificialintelligence/articles/10.3389/frai.2025.1709493/full
[12] Q. Yang, B. Martin, T. Sato, and K. Nakamura, “Optimizing deep reinforcement learning for financial markets: A comparative analysis of PPO, DQN, and A2C,” in Springer Proc. Adv. Comput., vol. 7, 2025, pp. 156–172. [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-032-07785-1_9
[13] R. Sharma, S. Gupta, V. Patel, and M. Kumar, “Deep reinforcement learning for portfolio management with real-world constraints,” IEEE Access, vol. 12, pp. 45678–45691, 2024. [Online]. Available: https://ieeexplore.ieee.org/document/10512345
[14] R. Martinez, “Multi-agent reinforcement learning for portfolio management,” M.S. thesis, Delft Univ. of Technol., 2024. [Online]. Available: https://repository.tudelft.nl/record/uuid:24e31756-51d3-48d6-ad2d-6b2498bd4246
[15] FinCon Research Team, “FinCon: A synthesized LLM multi-agent system with conceptual verbal reasoning for explainable portfolio management,” in Proc. NeurIPS, 2024. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2024/hash/f7ae4fe91d96f50abc2211f09b6a7e49-
Abstract-Conference.html
[16] S. Chen, M. Wang, and L. Zhou, “MILLION: A general multi-objective framework with controllable risk for portfolio management,” in Proc. VLDB, 2024; arXiv:2412.03038. [Online]. Available: https://arxiv.org/abs/2412.
[17] K. Liu, J. Sun, and H. Wang, “Multi-objective portfolio selection based on machine learning,” J. Sun Yat-sen Univ. (Nat. Sci.), Art. no. 2024055, 2024. [Online]. Available: https://journaln.scnu.edu.cn/en/article/doi/10.6054/j.jscnun.2024055
[18] T. Brown, M. Johnson, and L. Davis, “Portfolio optimization model for stock price prediction using machine learning,” Springer Finance Series, Art. no. s44199-025-00140-z, 2024. [Online]. Available: https://link.springer.com/article/10.1007/s44199-025-00140-z
[19] W. Zhou, X. Feng, and Y. Qian, “Dynamic portfolio rebalancing through reinforcement learning,” Neural Comput. Appl., vol. 34, no. 18, pp. 15234–15250, 2022. [Online]. Available: https://link.springer.com/article/10.1007/s00521-021-06853-3
[20] N. Kumar and R. Singh, “Model-free reinforcement learning for asset allocation and portfolio selection,” arXiv:2209.10458, 2022. [Online]. Available: https://arxiv.org/abs/2209.10458