"Social"的相关文档

Towards Understanding and Mitigating Social Biases in Language Models
TowardsUnderstandingandMitigatingSocialBiasesinLanguageModelsPaulPuLiang1ChiyuWu1Louis-PhilippeMorency1RuslanSalakhutdinov1AbstractZhaoetal.,2017).Morerecently,languagemodels(LMs)areincreasinglyuse...
and in Towards Understanding Mitigating
2023-11-16 19:42:12965963.33 KB26
下载文档
Emergent Social Learning via Multi-agent Reinforcement Learning
EmergentSocialLearningviaMulti-agentReinforcementLearningKamalNdousse1DouglasEck2SergeyLevine23NatashaJaques23AbstractHumansareabletolearnfromoneanotherwithoutdirectaccesstotheexperiencesormemories...
Learning Reinforcement via Multi-Agent Social
2023-11-16 18:38:008861.26 MB24
下载文档
Optimizing Long-term Social Welfare in Recommender Systems A Constrained Matching Approach
OptimizingLong-termSocialWelfareinRecommenderSystems:AConstrainedMatchingApproachMartinMladenov1ElliotCreager23OmerBen-Porat4†KevinSwersky1RichardZemel23CraigBoutilier1Abstractvideo),typicallyrely...
in Systems Long-term Optimizing Social
2023-11-14 21:45:45682762.3 KB19
下载文档
Learning Opinions in Social Networks
LearningOpinionsinSocialNetworksVincentConitzer1DebmalyaPanigrahi1HanruiZhang1Abstractstronglyaffectsuserv,andweknowthatuseruisawareofourproduct,thenwearequitesurethatuservisalsoWestudytheproblemof...
Learning Networks in Opinions Social
2023-11-14 21:44:541909284.51 KB2
下载文档
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
SocialInﬂuenceasIntrinsicMotivationforMulti-AgentDeepReinforcementLearningNatashaJaques12AngelikiLazaridou2EdwardHughes2CaglarGulcehre2PedroA.Ortega2DJStrouse3JoelZ.Leibo2NandodeFreitas2Abstractac...
for Multi-Agent Influence as Social
2023-11-13 14:48:341718653.83 KB9
下载文档

首页上页 1 下页尾页

Towards Understanding and Mitigating Social Biases in Language Models

Emergent Social Learning via Multi-agent Reinforcement Learning

Optimizing Long-term Social Welfare in Recommender Systems A Constrained Matching Approach

Learning Opinions in Social Networks

Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning