Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381587452> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4381587452 abstract "Automatic bill payment is an important part of business operations in fintech companies. The practice of deduction was mainly based on the total amount or heuristic search by dividing the bill into smaller parts to deduct as much as possible. This article proposes an end-to-end approach of automatically learning the optimal deduction paths (deduction amount in order), which reduces the cost of manual path design and maximizes the amount of successful deduction. Specifically, in view of the large search space of the paths and the extreme sparsity of historical successful deduction records, we propose a deep hierarchical reinforcement learning approach which abstracts the action into a two-level hierarchical space: an upper agent that determines the number of steps of deductions each day and a lower agent that decides the amount of deduction at each step. In such a way, the action space is structured via prior knowledge and the exploration space is reduced. Moreover, the inherited information incompleteness of the business makes the environment just partially observable. To be precise, the deducted amounts indicate merely the lower bounds of the available account balance. To this end, we formulate the problem as a partially observable Markov decision problem (POMDP) and employ an environment correction algorithm based on the characteristics of the business. In the world's largest electronic payment business, we have verified the effectiveness of this scheme offline and deployed it online to serve millions of users." @default.
- W4381587452 created "2023-06-22" @default.
- W4381587452 creator A5015102287 @default.
- W4381587452 creator A5021671895 @default.
- W4381587452 creator A5027261801 @default.
- W4381587452 creator A5030980879 @default.
- W4381587452 creator A5034826329 @default.
- W4381587452 creator A5037677450 @default.
- W4381587452 creator A5042259471 @default.
- W4381587452 creator A5054313662 @default.
- W4381587452 creator A5072815126 @default.
- W4381587452 date "2023-06-16" @default.
- W4381587452 modified "2023-09-25" @default.
- W4381587452 title "Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction" @default.
- W4381587452 doi "https://doi.org/10.48550/arxiv.2306.10083" @default.
- W4381587452 hasPublicationYear "2023" @default.
- W4381587452 type Work @default.
- W4381587452 citedByCount "0" @default.
- W4381587452 crossrefType "posted-content" @default.
- W4381587452 hasAuthorship W4381587452A5015102287 @default.
- W4381587452 hasAuthorship W4381587452A5021671895 @default.
- W4381587452 hasAuthorship W4381587452A5027261801 @default.
- W4381587452 hasAuthorship W4381587452A5030980879 @default.
- W4381587452 hasAuthorship W4381587452A5034826329 @default.
- W4381587452 hasAuthorship W4381587452A5037677450 @default.
- W4381587452 hasAuthorship W4381587452A5042259471 @default.
- W4381587452 hasAuthorship W4381587452A5054313662 @default.
- W4381587452 hasAuthorship W4381587452A5072815126 @default.
- W4381587452 hasBestOaLocation W43815874521 @default.
- W4381587452 hasConcept C105795698 @default.
- W4381587452 hasConcept C106189395 @default.
- W4381587452 hasConcept C111919701 @default.
- W4381587452 hasConcept C119857082 @default.
- W4381587452 hasConcept C121332964 @default.
- W4381587452 hasConcept C126255220 @default.
- W4381587452 hasConcept C136764020 @default.
- W4381587452 hasConcept C145097563 @default.
- W4381587452 hasConcept C154945302 @default.
- W4381587452 hasConcept C159886148 @default.
- W4381587452 hasConcept C163836022 @default.
- W4381587452 hasConcept C17098449 @default.
- W4381587452 hasConcept C173801870 @default.
- W4381587452 hasConcept C199360897 @default.
- W4381587452 hasConcept C2777735758 @default.
- W4381587452 hasConcept C2778572836 @default.
- W4381587452 hasConcept C2780791683 @default.
- W4381587452 hasConcept C33923547 @default.
- W4381587452 hasConcept C41008148 @default.
- W4381587452 hasConcept C62520636 @default.
- W4381587452 hasConcept C97541855 @default.
- W4381587452 hasConcept C98763669 @default.
- W4381587452 hasConceptScore W4381587452C105795698 @default.
- W4381587452 hasConceptScore W4381587452C106189395 @default.
- W4381587452 hasConceptScore W4381587452C111919701 @default.
- W4381587452 hasConceptScore W4381587452C119857082 @default.
- W4381587452 hasConceptScore W4381587452C121332964 @default.
- W4381587452 hasConceptScore W4381587452C126255220 @default.
- W4381587452 hasConceptScore W4381587452C136764020 @default.
- W4381587452 hasConceptScore W4381587452C145097563 @default.
- W4381587452 hasConceptScore W4381587452C154945302 @default.
- W4381587452 hasConceptScore W4381587452C159886148 @default.
- W4381587452 hasConceptScore W4381587452C163836022 @default.
- W4381587452 hasConceptScore W4381587452C17098449 @default.
- W4381587452 hasConceptScore W4381587452C173801870 @default.
- W4381587452 hasConceptScore W4381587452C199360897 @default.
- W4381587452 hasConceptScore W4381587452C2777735758 @default.
- W4381587452 hasConceptScore W4381587452C2778572836 @default.
- W4381587452 hasConceptScore W4381587452C2780791683 @default.
- W4381587452 hasConceptScore W4381587452C33923547 @default.
- W4381587452 hasConceptScore W4381587452C41008148 @default.
- W4381587452 hasConceptScore W4381587452C62520636 @default.
- W4381587452 hasConceptScore W4381587452C97541855 @default.
- W4381587452 hasConceptScore W4381587452C98763669 @default.
- W4381587452 hasLocation W43815874521 @default.
- W4381587452 hasOpenAccess W4381587452 @default.
- W4381587452 hasPrimaryLocation W43815874521 @default.
- W4381587452 hasRelatedWork W1563041104 @default.
- W4381587452 hasRelatedWork W2010557618 @default.
- W4381587452 hasRelatedWork W2033606355 @default.
- W4381587452 hasRelatedWork W2078617542 @default.
- W4381587452 hasRelatedWork W2140332127 @default.
- W4381587452 hasRelatedWork W2913022628 @default.
- W4381587452 hasRelatedWork W4309864858 @default.
- W4381587452 hasRelatedWork W4323767801 @default.
- W4381587452 hasRelatedWork W4324119149 @default.
- W4381587452 hasRelatedWork W4327667434 @default.
- W4381587452 isParatext "false" @default.
- W4381587452 isRetracted "false" @default.
- W4381587452 workType "article" @default.