IDEAS home Printed from https://ideas.repec.org/p/arx/papers/1712.01137.html
   My bibliography  Save this paper

Inferring agent objectives at different scales of a complex adaptive system

Author

Listed:
  • Dieter Hendricks
  • Adam Cobb
  • Richard Everett
  • Jonathan Downing
  • Stephen J. Roberts

Abstract

We introduce a framework to study the effective objectives at different time scales of financial market microstructure. The financial market can be regarded as a complex adaptive system, where purposeful agents collectively and simultaneously create and perceive their environment as they interact with it. It has been suggested that multiple agent classes operate in this system, with a non-trivial hierarchy of top-down and bottom-up causation classes with different effective models governing each level. We conjecture that agent classes may in fact operate at different time scales and thus act differently in response to the same perceived market state. Given scale-specific temporal state trajectories and action sequences estimated from aggregate market behaviour, we use Inverse Reinforcement Learning to compute the effective reward function for the aggregate agent class at each scale, allowing us to assess the relative attractiveness of feature vectors across different scales. Differences in reward functions for feature vectors may indicate different objectives of market participants, which could assist in finding the scale boundary for agent classes. This has implications for learning algorithms operating in this domain.

Suggested Citation

  • Dieter Hendricks & Adam Cobb & Richard Everett & Jonathan Downing & Stephen J. Roberts, 2017. "Inferring agent objectives at different scales of a complex adaptive system," Papers 1712.01137, arXiv.org.
    • Handle: RePEc:arx:papers:1712.01137
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/1712.01137
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. James B. T. Sanders & J. Doyne Farmer & Tobias Galla, 2016. "The prevalence of chaotic dynamics in games with many players," Papers 1612.08111, arXiv.org.
    2. D. Hendricks & T. Gebbie & D. Wilcox, 2016. "Detecting intraday financial market states using temporal clustering," Quantitative Finance, Taylor & Francis Journals, vol. 16(11), pages 1657-1678, November.
    3. Diane Wilcox & Tim Gebbie, 2014. "Hierarchical causality in financial economics," Papers 1408.5585, arXiv.org, revised Sep 2014.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Jacobo Roa-Vicens & Yuanbo Wang & Virgile Mison & Yarin Gal & Ricardo Silva, 2019. "Adversarial recovery of agent rewards from latent spaces of the limit order book," Papers 1912.04242, arXiv.org.
    2. Babak Mahdavi-Damghani & Konul Mustafayeva & Stephen Roberts & Cristin Buescu, 2018. "Portfolio Optimization for Cointelated Pairs: SDEs vs. Machine Learning," Papers 1812.10183, arXiv.org, revised Oct 2019.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Patrick Chang & Roger Bukuru & Tim Gebbie, 2019. "Revisiting the Epps effect using volume time averaging: An exercise in R," Papers 1912.02416, arXiv.org, revised Feb 2020.
    2. Tim Gebbie & Fayyaaz Loonat, 2016. "Learning zero-cost portfolio selection with pattern matching," Papers 1605.04600, arXiv.org.
    3. Yelibi, Lionel & Gebbie, Tim, 2020. "Fast Super-Paramagnetic Clustering," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 551(C).
    4. Ivan Jericevich & Dharmesh Sing & Tim Gebbie, 2021. "CoinTossX: An open-source low-latency high-throughput matching engine," Papers 2102.10925, arXiv.org.
    5. Fayyaaz Loonat & Tim Gebbie, 2018. "Learning zero-cost portfolio selection with pattern matching," PLOS ONE, Public Library of Science, vol. 13(9), pages 1-38, September.
    6. Donovan Platt & Tim Gebbie, 2016. "Can Agent-Based Models Probe Market Microstructure?," Papers 1611.08510, arXiv.org, revised Aug 2017.
    7. Patrick Chang & Etienne Pienaar & Tim Gebbie, 2020. "Using the Epps effect to detect discrete processes," Papers 2005.10568, arXiv.org, revised Oct 2021.
    8. Dicks, Matthew & Paskaramoorthy, Andrew & Gebbie, Tim, 2024. "A simple learning agent interacting with an agent-based market model," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 633(C).
    9. Dieter Hendricks & Tim Gebbie & Diane Wilcox, 2015. "Detecting intraday financial market states using temporal clustering," Papers 1508.04900, arXiv.org, revised Feb 2017.
    10. Joel da Costa & Tim Gebbie, 2020. "Learning low-frequency temporal patterns for quantitative trading," Papers 2008.09481, arXiv.org.
    11. George Barnes & Sanjaye Ramgoolam & Michael Stephanou, 2023. "Permutation invariant Gaussian matrix models for financial correlation matrices," Papers 2306.04569, arXiv.org.
    12. Patrick Chang & Etienne Pienaar & Tim Gebbie, 2020. "Malliavin-Mancino estimators implemented with non-uniform fast Fourier transforms," Papers 2003.02842, arXiv.org, revised Nov 2020.
    13. Andrew Paskaramoorthy & Terence van Zyl & Tim Gebbie, 2020. "A Framework for Online Investment Algorithms," Papers 2003.13360, arXiv.org.
    14. Pier Francesco Procacci & Tomaso Aste, 2018. "Forecasting market states," Papers 1807.05836, arXiv.org, revised May 2019.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:1712.01137. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.