Towards a fully RL-based Market Simulator

被引：8

作者：

Ardon, Leo ^{[1
]}

Vadori, Nelson ^{[1
]}

Spooner, Thomas ^{[1
]}

Xu, Mengda ^{[1
]}

Vann, Jared ^{[1
]}

Ganesh, Sumitra ^{[1
]}

机构：

[1] JP Morgan AI Res, Pittsburgh, PA 15213 USA

来源：

ICAIF 2021: THE SECOND ACM INTERNATIONAL CONFERENCE ON AI IN FINANCE | 2021年

关键词：

multi-agent; reinforcement learning; market making;

D O I：

10.1145/3490354.3494372

中图分类号：

F8 [财政、金融];

学科分类号：

0202 ;

摘要：

We present a new financial framework where two families of RL-based agents representing the Liquidity Providers and Liquidity Takers learn simultaneously to satisfy their objective. Thanks to a parametrized reward formulation and the use of Deep RL, each group learns a shared policy able to generalize and interpolate over a wide range of behaviors. This is a step towards a fully RL-based market simulator replicating complex market conditions particularly suited to study the dynamics of the financial market under various scenarios.

引用

页数：9

共 18 条

[1] DEALERSHIP MARKET - MARKET-MAKING WITH INVENTORY [J].

AMIHUD, Y ;

MENDELSON, H .

JOURNAL OF FINANCIAL ECONOMICS, 1980, 8 (01) :31-53

[2] High-frequency trading in a limit order book [J].

Avellaneda, Marco ;

Stoikov, Sasha .

QUANTITATIVE FINANCE, 2008, 8 (03) :217-224

[3]

Bernstein D. S., 2000, P 16 C UNCERTAINTY A, P32

[4]

Brockman G, 2016, Arxiv, DOI arXiv:1606.01540

[5]

Chan N. T., 2001, ELECT MARKET MAKER

[6]

Cont R, 2021, OPER RES, V2021

[7]

Cui W., 2012, 2012 IEEE C COMP INT, DOI DOI 10.1109/CIFER.2012.6327798

[8]

Das Sanmay, 2003, P INT WORKSHOP COMPL

[9]

Ganesh S, 2019, Arxiv, DOI [arXiv:1911.05892, DOI 10.48550/ARXIV.1911.05892]

[10] MARKET MICROSTRUCTURE [J].

GARMAN, MB .

JOURNAL OF FINANCIAL ECONOMICS, 1976, 3 (03) :257-275

← 1 2 →