Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320341716> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4320341716 abstract "With the recent prevalence of reinforcement learning (RL), there have been tremendous interests in utilizing RL for ads allocation in recommendation platforms (e.g., e-commerce and news feed sites). To achieve better allocation, the input of recent RL-based ads allocation methods is upgraded from point-wise single item to list-wise item arrangement. However, this also results in a high-dimensional space of state-action pairs, making it difficult to learn list-wise representations with good generalization ability. This further hinders the exploration of RL agents and causes poor sample efficiency. To address this problem, we propose a novel RL-based approach for ads allocation which learns better list-wise representations by leveraging task-specific signals on Meituan food delivery platform. Specifically, we propose three different auxiliary tasks based on reconstruction, prediction, and contrastive learning respectively according to prior domain knowledge on ads allocation. We conduct extensive experiments on Meituan food delivery platform to evaluate the effectiveness of the proposed auxiliary tasks. Both offline and online experimental results show that the proposed method can learn better list-wise representations and achieve higher revenue for the platform compared to the state-of-the-art baselines." @default.
- W4320341716 created "2023-02-13" @default.
- W4320341716 creator A5008904028 @default.
- W4320341716 creator A5027645208 @default.
- W4320341716 creator A5036011098 @default.
- W4320341716 creator A5036945708 @default.
- W4320341716 creator A5046454314 @default.
- W4320341716 creator A5078046664 @default.
- W4320341716 creator A5080460228 @default.
- W4320341716 creator A5088642582 @default.
- W4320341716 date "2022-04-02" @default.
- W4320341716 modified "2023-10-16" @default.
- W4320341716 title "Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks" @default.
- W4320341716 doi "https://doi.org/10.48550/arxiv.2204.00888" @default.
- W4320341716 hasPublicationYear "2022" @default.
- W4320341716 type Work @default.
- W4320341716 citedByCount "0" @default.
- W4320341716 crossrefType "posted-content" @default.
- W4320341716 hasAuthorship W4320341716A5008904028 @default.
- W4320341716 hasAuthorship W4320341716A5027645208 @default.
- W4320341716 hasAuthorship W4320341716A5036011098 @default.
- W4320341716 hasAuthorship W4320341716A5036945708 @default.
- W4320341716 hasAuthorship W4320341716A5046454314 @default.
- W4320341716 hasAuthorship W4320341716A5078046664 @default.
- W4320341716 hasAuthorship W4320341716A5080460228 @default.
- W4320341716 hasAuthorship W4320341716A5088642582 @default.
- W4320341716 hasBestOaLocation W43203417161 @default.
- W4320341716 hasConcept C105795698 @default.
- W4320341716 hasConcept C119857082 @default.
- W4320341716 hasConcept C121955636 @default.
- W4320341716 hasConcept C134306372 @default.
- W4320341716 hasConcept C144133560 @default.
- W4320341716 hasConcept C154945302 @default.
- W4320341716 hasConcept C162324750 @default.
- W4320341716 hasConcept C177148314 @default.
- W4320341716 hasConcept C17744445 @default.
- W4320341716 hasConcept C187736073 @default.
- W4320341716 hasConcept C195487862 @default.
- W4320341716 hasConcept C199539241 @default.
- W4320341716 hasConcept C2524010 @default.
- W4320341716 hasConcept C2776359362 @default.
- W4320341716 hasConcept C2780451532 @default.
- W4320341716 hasConcept C28719098 @default.
- W4320341716 hasConcept C33923547 @default.
- W4320341716 hasConcept C36503486 @default.
- W4320341716 hasConcept C41008148 @default.
- W4320341716 hasConcept C72434380 @default.
- W4320341716 hasConcept C94625758 @default.
- W4320341716 hasConcept C97541855 @default.
- W4320341716 hasConceptScore W4320341716C105795698 @default.
- W4320341716 hasConceptScore W4320341716C119857082 @default.
- W4320341716 hasConceptScore W4320341716C121955636 @default.
- W4320341716 hasConceptScore W4320341716C134306372 @default.
- W4320341716 hasConceptScore W4320341716C144133560 @default.
- W4320341716 hasConceptScore W4320341716C154945302 @default.
- W4320341716 hasConceptScore W4320341716C162324750 @default.
- W4320341716 hasConceptScore W4320341716C177148314 @default.
- W4320341716 hasConceptScore W4320341716C17744445 @default.
- W4320341716 hasConceptScore W4320341716C187736073 @default.
- W4320341716 hasConceptScore W4320341716C195487862 @default.
- W4320341716 hasConceptScore W4320341716C199539241 @default.
- W4320341716 hasConceptScore W4320341716C2524010 @default.
- W4320341716 hasConceptScore W4320341716C2776359362 @default.
- W4320341716 hasConceptScore W4320341716C2780451532 @default.
- W4320341716 hasConceptScore W4320341716C28719098 @default.
- W4320341716 hasConceptScore W4320341716C33923547 @default.
- W4320341716 hasConceptScore W4320341716C36503486 @default.
- W4320341716 hasConceptScore W4320341716C41008148 @default.
- W4320341716 hasConceptScore W4320341716C72434380 @default.
- W4320341716 hasConceptScore W4320341716C94625758 @default.
- W4320341716 hasConceptScore W4320341716C97541855 @default.
- W4320341716 hasLocation W43203417161 @default.
- W4320341716 hasOpenAccess W4320341716 @default.
- W4320341716 hasPrimaryLocation W43203417161 @default.
- W4320341716 hasRelatedWork W2101355568 @default.
- W4320341716 hasRelatedWork W2350784623 @default.
- W4320341716 hasRelatedWork W2951308022 @default.
- W4320341716 hasRelatedWork W2989932438 @default.
- W4320341716 hasRelatedWork W3022038857 @default.
- W4320341716 hasRelatedWork W4285428938 @default.
- W4320341716 hasRelatedWork W4288317198 @default.
- W4320341716 hasRelatedWork W4293469469 @default.
- W4320341716 hasRelatedWork W4302011254 @default.
- W4320341716 hasRelatedWork W4319083788 @default.
- W4320341716 isParatext "false" @default.
- W4320341716 isRetracted "false" @default.
- W4320341716 workType "article" @default.