Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211700439> ?p ?o ?g. }
- W3211700439 endingPage "5373" @default.
- W3211700439 startingPage "5361" @default.
- W3211700439 abstract "In this article, we study the problem of guaranteed display ads (GDAs) allocation, which requires proactively allocate display ads to different impressions to fulfill their impression demands indicated in the contracts. Existing methods for this problem either assume the impressions that are static or solely consider a specific ad's benefits. Thus, it is hard to generalize to the industrial production scenario where the impressions are dynamical and large-scale, and the overall allocation optimality of all the considered GDAs is required. To bridge this gap, we formulate this problem as a sequential decision-making problem in the scope of multiagent reinforcement learning (MARL), by assigning an allocation agent to each ad and coordinating all the agents for allocating GDAs. The inputs are the states (e.g., the demands of the ad and the remaining time steps for displaying the ads) of each ad and the impressions at different time steps, and the outputs are the display ratios of each ad for each impression. Specifically, we propose a novel hierarchical MARL (HMARL) method that creates hierarchies over the agent policies to handle a large number of ads and the dynamics of impressions. HMARL contains: 1) a manager policy to navigate the agent to choose an appropriate subpolicy and 2) a set of subpolicies that let the agents perform diverse conditioning on their states. Extensive experiments on three real-world data sets from the Tencent advertising platform with tens of millions of records demonstrate significant improvements of HMARL over state-of-the-art approaches." @default.
- W3211700439 created "2021-11-22" @default.
- W3211700439 creator A5005503474 @default.
- W3211700439 creator A5020958723 @default.
- W3211700439 creator A5020980410 @default.
- W3211700439 creator A5025415809 @default.
- W3211700439 creator A5026633464 @default.
- W3211700439 creator A5029484872 @default.
- W3211700439 creator A5055663663 @default.
- W3211700439 creator A5068865316 @default.
- W3211700439 creator A5090720315 @default.
- W3211700439 date "2022-10-01" @default.
- W3211700439 modified "2023-09-27" @default.
- W3211700439 title "Hierarchical Multiagent Reinforcement Learning for Allocating Guaranteed Display Ads" @default.
- W3211700439 cites W1120219466 @default.
- W3211700439 cites W1641379095 @default.
- W3211700439 cites W1769120835 @default.
- W3211700439 cites W1907356258 @default.
- W3211700439 cites W1972169135 @default.
- W3211700439 cites W1973976093 @default.
- W3211700439 cites W1982678075 @default.
- W3211700439 cites W2044905589 @default.
- W3211700439 cites W2096145798 @default.
- W3211700439 cites W2107112577 @default.
- W3211700439 cites W2109910161 @default.
- W3211700439 cites W2112741516 @default.
- W3211700439 cites W2121517924 @default.
- W3211700439 cites W2148352389 @default.
- W3211700439 cites W2149822245 @default.
- W3211700439 cites W2170675255 @default.
- W3211700439 cites W2183373924 @default.
- W3211700439 cites W2539201403 @default.
- W3211700439 cites W2602275733 @default.
- W3211700439 cites W2606378794 @default.
- W3211700439 cites W2768629321 @default.
- W3211700439 cites W2974685809 @default.
- W3211700439 cites W3124383212 @default.
- W3211700439 cites W4252172911 @default.
- W3211700439 doi "https://doi.org/10.1109/tnnls.2021.3070484" @default.
- W3211700439 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33999823" @default.
- W3211700439 hasPublicationYear "2022" @default.
- W3211700439 type Work @default.
- W3211700439 sameAs 3211700439 @default.
- W3211700439 citedByCount "0" @default.
- W3211700439 crossrefType "journal-article" @default.
- W3211700439 hasAuthorship W3211700439A5005503474 @default.
- W3211700439 hasAuthorship W3211700439A5020958723 @default.
- W3211700439 hasAuthorship W3211700439A5020980410 @default.
- W3211700439 hasAuthorship W3211700439A5025415809 @default.
- W3211700439 hasAuthorship W3211700439A5026633464 @default.
- W3211700439 hasAuthorship W3211700439A5029484872 @default.
- W3211700439 hasAuthorship W3211700439A5055663663 @default.
- W3211700439 hasAuthorship W3211700439A5068865316 @default.
- W3211700439 hasAuthorship W3211700439A5090720315 @default.
- W3211700439 hasConcept C100776233 @default.
- W3211700439 hasConcept C11413529 @default.
- W3211700439 hasConcept C126322002 @default.
- W3211700439 hasConcept C127413603 @default.
- W3211700439 hasConcept C154945302 @default.
- W3211700439 hasConcept C177264268 @default.
- W3211700439 hasConcept C199360897 @default.
- W3211700439 hasConcept C2778012447 @default.
- W3211700439 hasConcept C29202148 @default.
- W3211700439 hasConcept C31258907 @default.
- W3211700439 hasConcept C41008148 @default.
- W3211700439 hasConcept C42475967 @default.
- W3211700439 hasConcept C48103436 @default.
- W3211700439 hasConcept C71924100 @default.
- W3211700439 hasConcept C97541855 @default.
- W3211700439 hasConceptScore W3211700439C100776233 @default.
- W3211700439 hasConceptScore W3211700439C11413529 @default.
- W3211700439 hasConceptScore W3211700439C126322002 @default.
- W3211700439 hasConceptScore W3211700439C127413603 @default.
- W3211700439 hasConceptScore W3211700439C154945302 @default.
- W3211700439 hasConceptScore W3211700439C177264268 @default.
- W3211700439 hasConceptScore W3211700439C199360897 @default.
- W3211700439 hasConceptScore W3211700439C2778012447 @default.
- W3211700439 hasConceptScore W3211700439C29202148 @default.
- W3211700439 hasConceptScore W3211700439C31258907 @default.
- W3211700439 hasConceptScore W3211700439C41008148 @default.
- W3211700439 hasConceptScore W3211700439C42475967 @default.
- W3211700439 hasConceptScore W3211700439C48103436 @default.
- W3211700439 hasConceptScore W3211700439C71924100 @default.
- W3211700439 hasConceptScore W3211700439C97541855 @default.
- W3211700439 hasFunder F4320335777 @default.
- W3211700439 hasIssue "10" @default.
- W3211700439 hasLocation W32117004391 @default.
- W3211700439 hasLocation W32117004392 @default.
- W3211700439 hasOpenAccess W3211700439 @default.
- W3211700439 hasPrimaryLocation W32117004391 @default.
- W3211700439 hasRelatedWork W1562959674 @default.
- W3211700439 hasRelatedWork W2923653485 @default.
- W3211700439 hasRelatedWork W2952472710 @default.
- W3211700439 hasRelatedWork W2957776456 @default.
- W3211700439 hasRelatedWork W3009671569 @default.
- W3211700439 hasRelatedWork W3089192431 @default.
- W3211700439 hasRelatedWork W3212159549 @default.
- W3211700439 hasRelatedWork W4289712363 @default.