|
000
| 02290nam 2200361zi 4500 |
|---|
| 001 | 9.895997 |
|---|
| 003 | CaOODSP |
|---|
| 005 | 20221107174206 |
|---|
| 006 | m o d f |
|---|
| 007 | cr cn||||||||| |
|---|
| 008 | 210201e20210201oncd ob f000 0 eng d |
|---|
| 040 | |aCaOODSP|beng|erda|cCaOODSP |
|---|
| 086 | 1 |aFB3-5/2021-7E-PDF |
|---|
| 100 | 1 |aCastro, Pablo S., |eauthor. |
|---|
| 245 | 10|aEstimating policy functions in payments systems using reinforcement learning / |cby Pablo S. Castro, Ajit Desai, Han Du, Rodney Garratt and Francisco Rivadeneyra. |
|---|
| 264 | 1|aOttawa, Ontario, Canada : |bBank of Canada = Banque du Canada, |cFebruary 1, 2021. |
|---|
| 264 | 4|c©2021 |
|---|
| 300 | |a1 online resource (ii, 40 pages) : |bcolour graphs |
|---|
| 336 | |atext|btxt|2rdacontent |
|---|
| 337 | |acomputer|bc|2rdamedia |
|---|
| 338 | |aonline resource|bcr|2rdacarrier |
|---|
| 490 | 1 |aStaff working paper = |aDocument de travail du personnel, |x1701-9397 ; |v2021-7 |
|---|
| 504 | |aIncludes bibliographical references (pages 20-21). |
|---|
| 520 | 3 |a"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"--Abstract, page ii. |
|---|
| 650 | 0|aBanks and banking. |
|---|
| 650 | 0|aReinforcement learning. |
|---|
| 650 | 0|aPayment. |
|---|
| 650 | 6|aBanques. |
|---|
| 650 | 6|aApprentissage par renforcement (Intelligence artificielle) |
|---|
| 650 | 6|aPaiement. |
|---|
| 710 | 2 |aBank of Canada, |eissuing body. |
|---|
| 830 | #0|aStaff working paper (Bank of Canada)|v2021-7.|w(CaOODSP)9.806221 |
|---|
| 856 | 40|qPDF|s1.36 MB|uhttps://publications.gc.ca/collections/collection_2021/banque-bank-canada/FB3-5-2021-7-eng.pdf |
|---|