Sign up

Research paper

Optimal execution in a fractional setting with reinforcement learning

3 authors
  1. Matthieu Garcin
  2. Jiang Pu
  3. Thomas Verrier
Venue
arXiv (Cornell University)
Year
2026
Publication date
2026-11-08

Abstract

Held from OpenAlex
We consider the problem of optimal liquidation with linear market impact, as in the seminal work of Almgren and Chriss, but with an asset driven by a fractional Brownian motion. For $H \neq 1/2$, we observe that the deterministic solution given by Almgren and Chriss is no longer optimal. We develop a strategy to exploit the information induced by the correlation between price increments. The strategy is derived from a policy gradient algorithm, parameterized by a neural network, trained to maximise the CARA utility, for which our method allows for significant improvements.

Attribution

Matthieu Garcin, Jiang Pu, Thomas Verrier — Optimal execution in a fractional setting with reinforcement learning (2026), arXiv (Cornell University). Original: DOI 10.48550/arxiv.2611.11373. Metadata and abstract supplied by OpenAlex (CC0). OpenAlex record: https://openalex.org/W7225697400. Harvested 2026-11-12; record openalex-works-select.v1 + eccdedebf84a; published 2026-11-12.

Identifiers

doi
https://doi.org/10.48550/arxiv.2611.11373
openalex
https://openalex.org/W7225697400

Research topics

Replications

No Quantellect replication yet

Audited strategies and their receipts will appear here after a separate strategy release.

Citation export

Text remains available without JavaScript

Plain text

Matthieu Garcin, Jiang Pu, & Thomas Verrier (2026). Optimal execution in a fractional setting with reinforcement learning. arXiv (Cornell University).

BibTeX

@article{optimal-execution-in-a-fractional-setting-with-reinforcement-learning-1808915,
  title = {Optimal execution in a fractional setting with reinforcement learning},
  author = {Matthieu Garcin and Jiang Pu and Thomas Verrier},
  journal = {arXiv (Cornell University)},
  year = {2026},
  doi = {10.48550/arxiv.2611.11373},
}

RIS

TY  - JOUR
AU  - Matthieu Garcin
AU  - Jiang Pu
AU  - Thomas Verrier
TI  - Optimal execution in a fractional setting with reinforcement learning
JO  - arXiv (Cornell University)
PY  - 2026
DO  - 10.48550/arxiv.2611.11373
UR  - https://doi.org/10.48550/arxiv.2611.11373
ER  -