Estimating Policy Functions in Payments Systems Using Reinforcement Learning

Pablo S. Castro, Ajit Desai, Han Du, Rodney Garratt and Francisco Rivadeneyra

Staff Working Papers from Bank of Canada

Abstract: This paper uses reinforcement learning (RL) to approximate the policy rules of banks participating in a high-value payments system. The objective of the agents is to learn a policy function for the choice of amount of liquidity provided to the system at the beginning of the day. Individual choices have complex strategic effects precluding a closed form solution of the optimal policy, except in simple cases. We show that in a simplified two-agent setting, agents using reinforcement learning do learn the optimal policy that minimizes the cost of processing their individual payments. We also show that in more complex settings, both agents learn to reduce their liquidity costs. Our results show the applicability of RL to estimate best-response functions in real-world strategic games.

Keywords: Digital currencies and fintech; Financial institutions; Financial system regulation and policies; Payment clearing and settlement systems (search for similar items in EconPapers)
JEL-codes: A12 C7 D83 E42 E58 (search for similar items in EconPapers)
Pages: 42 pages
Date: 2021-02
New Economics Papers: this item is included in nep-cba, nep-mac, nep-ore and nep-pay
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://www.bankofcanada.ca/wp-content/uploads/2021/02/swp2021-7.pdf Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bca:bocawp:21-7

Access Statistics for this paper

More papers in Staff Working Papers from Bank of Canada 234 Wellington Street, Ottawa, Ontario, K1A 0G9, Canada. Contact information at EDIRC.
Bibliographic data for series maintained by ().