aiqbench analysis
Composing insight from the full article — this may take a moment.
Continuous-Time Reinforcement Learning for Asset-Liability Management
From arXiv
Full textarXiv:2509.23280v2 Announce Type: replace-cross Abstract: This paper proposes a novel approach for Asset-Liability Management (ALM) by employing continuous-time Reinforcement Learning (RL) with a linear-quadratic (LQ) formulation that incorporates both interim and terminal objectives. We develop a model-free, policy gradient-based soft actor-critic algorithm tailored to ALM for dynamically synchronizing assets and liabilities. To ensure an effective balance between exploration and exploitation with minimal tuning, we introduce adaptive exploration for the actor and scheduled exploration for the critic.
Our empirical study evaluates this approach against two enhanced traditional financial strategies, a model-based continuous-time RL method, and three state-of-the-art RL algorithms. Evaluated across 200 randomized market scenarios, our method achieves higher average rewards than all alternative strategies, with rapid initial gains and sustained superior performance. The outperformance stems not from complex neural networks or improved parameter estimation, but from directly learning the optimal ALM strategy without learning the environment.
Abstract:This paper proposes a novel approach for Asset-Liability Management (ALM) by employing continuous-time Reinforcement Learning (RL) with a linear-quadratic (LQ) formulation that incorporates both interim and terminal objectives. We develop a model-free, policy gradient-based soft actor-critic algorithm tailored to ALM for dynamically synchronizing assets and liabilities. To ensure an effective balance between exploration and exploitation with minimal tuning, we introduce adaptive exploration for the actor and scheduled exploration for the critic.
Our empirical study evaluates this approach against two enhanced traditional financial strategies, a model-based continuous-time RL method, and three state-of-the-art RL algorithms. Evaluated across 200 randomized market scenarios, our method achieves higher average rewards than all alternative strategies, with rapid initial gains and sustained superior performance. The outperformance stems not from complex neural networks or improved parameter estimation, but from directly learning the optimal ALM strategy without learning the environment.
8 pages, 2 figures. Updated publication information and corrected a typo in the caption of Figure 1
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC); Mathematical Finance (q-fin.MF)
arXiv:2509.23280 [cs.LG]
(or arXiv:2509.23280v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2509.23280 Focus to learn more arXiv-issued DOI via DataCite
Proceedings of the 6th ACM International Conference on AI in Finance (ICAIF 2025), pp. 360-368, 2025
https://doi.org/10.1145/3768292.3770337 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 286 words