# Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2003.03051 · HTML: https://mlsanity.com/paper/2003.03051/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2020.

## Built on by (most cited first, 21 of 21)

- [Reinforcement Learning for Quantitative Trading](https://mlsanity.com/paper/2109.13851/) (2021)
- [The Evolution of Reinforcement Learning in Quantitative Finance: A Survey](https://mlsanity.com/paper/2408.10932/) (2024)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Dynamic Compressing Prompts for Efficient Inference of Large Language Models](https://mlsanity.com/paper/2504.11004/) (2025)
- [Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management](https://mlsanity.com/paper/2402.00515/) (2024)
- [Value Penalized Q-Learning for Recommender Systems](https://mlsanity.com/paper/2110.07923/) (2021)
- [The Recurrent Reinforcement Learning Crypto Agent](https://mlsanity.com/paper/2201.04699/) (2022)
- [Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent](https://mlsanity.com/paper/2407.14486/) (2024)
- [Deploying Offline Reinforcement Learning with Human Feedback](https://mlsanity.com/paper/2303.07046/) (2023)
- [QuantBench: Benchmarking AI Methods for Quantitative Investment](https://mlsanity.com/paper/2504.18600/) (2025)
- [Benchmarking Robustness of Deep Reinforcement Learning approaches to Online Portfolio Management](https://mlsanity.com/paper/2306.10950/) (2023)
- [WaveCorr: Correlation-savvy Deep Reinforcement Learning for Portfolio Management](https://mlsanity.com/paper/2109.07005/) (2021)
- [Data Cross-Segmentation for Improved Generalization in Reinforcement Learning Based Algorithmic Trading](https://mlsanity.com/paper/2307.09377/) (2023)
- [Least Squares Maximum and Weighted Generalization-Memorization Machines](https://mlsanity.com/paper/2308.16456/) (2023)
- [Commodities Trading through Deep Policy Gradient Methods](https://mlsanity.com/paper/2309.00630/) (2023)
- [Developing An Attention-Based Ensemble Learning Framework for Financial Portfolio Optimisation](https://mlsanity.com/paper/2404.08935/) (2024)
- [Large Investment Model](https://mlsanity.com/paper/2408.10255/) (2024)
- [DeepAries: Adaptive Rebalancing Interval Selection for Enhanced Portfolio Selection](https://mlsanity.com/paper/2510.14985/) (2025)
- [The Enhanced Physics-Informed Kolmogorov-Arnold Networks: Applications of Newton's Laws in Financial Deep Reinforcement Learning (RL) Algorithms](https://mlsanity.com/paper/2602.01388/) (2026)
- [Regime-Adaptive Continual Learning for Portfolio Management](https://mlsanity.com/paper/2606.00143/) (2026)
- [Large-Scale Portfolio Optimization Problem Under Cardinality Constraint With Enhanced Multi-Objective Evolutionary Algorithms](https://mlsanity.com/paper/2607.09566/) (2026)

## Abstract (arXiv)

Portfolio Selection is an important real-world financial task and has attracted extensive attention in artificial intelligence communities. This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs. Most existing methods adopt handcraft features and/or consider no constraints for the costs, which may make them perform unsatisfactorily and fail to control both costs in practice. In this paper, we propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations, while a new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning. We theoretically analyze the near-optimality of the proposed reward, which shows that the growth rate of the policy regarding this reward function can approach the theoretical optimum. We also empirically evaluate the proposed method on real-world datasets. Promising results demonstrate the effectiveness and superiority of the proposed method in terms of profitability, cost-sensitivity and representation abilities.