Simplex Decomposition for Portfolio Allocation Constraints in Reinforcement Learning
On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance
Abstract (arXiv)
Portfolio optimization tasks describe sequential decision problems in which the investor's wealth is distributed across a set of assets. Allocation constraints are used to enforce minimal or maximal investments into particular subsets of assets to control for objectives such as limiting the portfolio's exposure to a certain sector due to environmental concerns. Although methods for constrained Reinforcement Learning (CRL) can optimize policies while considering allocation constraints, it can be observed that these general methods yield suboptimal results. In this paper, we propose a novel approach to handle allocation constraints based on a decomposition of the constraint action space into a set of unconstrained allocation problems. In particular, we examine this approach for the case of two constraints. For example, an investor may wish to invest at least a certain percentage of the portfolio into green technologies while limiting the investment in the fossil energy sector. We show that the action space of the task is equivalent to the decomposed action space, and introduce a new reinforcement learning (RL) approach CAOSD, which is built on top of the decomposition. The experimental evaluation on real-world Nasdaq-100 data demonstrates that our approach consistently outperforms state-of-the-art CRL benchmarks for portfolio optimization.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 19 references that are in the map. First posted on arXiv 16 Apr 2024.
Builds on
14 of 19 references.
References · 14
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2018Reward Constrained Policy Optimizationcited by 417
- 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 353
- 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
- 2019Stabilizing Transformers for Reinforcement Learningcited by 270
- 2018Safe Exploration in Continuous Action Spacescited by 247
- 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 145
- 2019IPO: Interior-point Policy Optimization under Constraintscited by 132
- 2017Action Branching Architectures for Deep Reinforcement Learningcited by 92
- 2022Penalized Proximal Policy Optimization for Safe Reinforcement Learningcited by 68
- 2017Discrete Sequential Prediction of Continuous Actions for Deep RLcited by 51
- 2018Hierarchical Approaches for Reinforcement Learning in Parameterized Action Spacecited by 15
2 more
Built on by
Citing papers per year: 2024: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025FinXplore: An Adaptive Deep Reinforcement Learning Framework for Balancing and Discovering Investment Opportunities
- 2026Reinforcement Learning for Risk-Sensitive Investment Management: a Free Energy--Entropy Duality Approach
- 2026Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization
- 2026Deep Reinforcement Learning Framework for Diversified Portfolio Management Across Global Equity Markets
- 2022Wall Street Tree Search: Risk-Aware Planning for Offline Reinforcement Learning
- 2025Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information
- 2023Towards Generalizable Reinforcement Learning for Trade Execution
- 2025Deep Reinforcement Learning for Optimal Asset Allocation Using DDPG with TiDE