Saved in:
Bibliographic Details
Main Author: Asadulaev, Arip
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.21707
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917518191362048
author Asadulaev, Arip
author_facet Asadulaev, Arip
contents We describe an adaptive market-making architecture that preserves the analytical structure of the Avellaneda--Stoikov framework while introducing a successor measure-style adaptation mechanism. In our paper we keep Avellaneda--Stoikov fast Hamilton--Jacobi--Bellman structure and make it adaptive to changing market regimes and trading objectives. The central idea is to separate market dynamics from the trading objective. The market state determines a low-dimensional set of Avellaneda--Stoikov parameters, while recent realized rewards determine a low-dimensional objective vector. The HJB forward map then converts this objective into optimal bid and ask quotes through a scalarization of future reward features.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21707
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zero-shot adaptation to order book dynamics
Asadulaev, Arip
Computational Engineering, Finance, and Science
Machine Learning
We describe an adaptive market-making architecture that preserves the analytical structure of the Avellaneda--Stoikov framework while introducing a successor measure-style adaptation mechanism. In our paper we keep Avellaneda--Stoikov fast Hamilton--Jacobi--Bellman structure and make it adaptive to changing market regimes and trading objectives. The central idea is to separate market dynamics from the trading objective. The market state determines a low-dimensional set of Avellaneda--Stoikov parameters, while recent realized rewards determine a low-dimensional objective vector. The HJB forward map then converts this objective into optimal bid and ask quotes through a scalarization of future reward features.
title Zero-shot adaptation to order book dynamics
topic Computational Engineering, Finance, and Science
Machine Learning
url https://arxiv.org/abs/2605.21707