"Successor"的相关文档

PsiPhi-Learning Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
PsiPhi-Learning:ReinforcementLearningwithDemonstrationsusingSuccessorFeaturesandInverseTemporalDifferenceLearningAngelosFilos1ClareLyle1YarinGal1SergeyLevine2NatashaJaques23GregoryFarquhar4Abstract...
Learning Using with Reinforcement Demonstrations
2023-11-16 19:28:359534.23 MB7
下载文档
Policy Caches with Successor Features
PolicyCacheswithSuccessorFeaturesMarkNemecek1RonaldParr1Abstracttaskswhichvaryintheirrewardfunctions,butwherethedynamicsremainthesame.Althoughlimitedinscope,thisTransferinreinforcementlearningisbas...
with Policy Features Successor Caches
2023-11-16 19:28:2919765.25 MB19
下载文档
APS Active Pretraining with Successor Features
APS:ActivePretrainingwithSuccessorFeaturesHaoLiu1PieterAbbeel1Abstract2019;Vinyalsetal.,2019;Badiaetal.,2020a)andsolvingcomplexroboticcontroltasks(Andrychowiczetal.,2017;Weintroduceanewunsupervised...
Active with Features Successor Pretraining
2023-11-16 18:00:178991.47 MB20
下载文档
A New Representation of Successor Features for Transfer across Dissimilar Environments
ANewRepresentationofSuccessorFeaturesforTransferacrossDissimilarEnvironmentsMajidAbdolshah1HungLe1ThommenKarimpanalGeorge1SunilGupta1SantuRana1SvethaVenkatesh1Abstractintoindependentsub-domains.How...
of for Transfer Representation New
2023-11-16 17:51:5611571.21 MB30
下载文档
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
TransferinDeepReinforcementLearningUsingSuccessorFeaturesandGeneralisedPolicyImprovementAndre´Barreto1DianaBorsa1JohnQuan1TomSchaul1DavidSilver1MatteoHessel1DanielMankowitz1AugustinZˇ´ıdek1Re´...
Learning Using Reinforcement Deep in
2023-11-13 12:00:5413771.59 MB27
下载文档

首页上页 1 下页尾页

PsiPhi-Learning Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

Policy Caches with Successor Features

APS Active Pretraining with Successor Features

A New Representation of Successor Features for Transfer across Dissimilar Environments

Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement