@prefix dcat: <http://www.w3.org/ns/dcat#> .
@prefix dct: <http://purl.org/dc/terms/> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix vcard: <http://www.w3.org/2006/vcard/ns#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .

<https://rec.harvest-normandie.data4citizen.com/dataset/oai-hal-hal-00644516v2> a dcat:Dataset ;
    dct:description """
              In the framework of Markov Decision Processes, off-policy learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly review on-policy learning algorithms of the literature (gradient-based and least-squares-based), adopting a unified algorithmic view. Then, we highlight a systematic approach for adapting them to off-policy learning with eligibility traces. This leads to some known algorithms - off-policy LSTD(λ), LSPE(λ), TD(λ), TDC/GQ(λ) - and suggests new extensions - off-policy FPKF(λ), BRM(λ), gBRM(λ), GTD2(λ). We describe a comprehensive algorithmic derivation of all algorithms in a recursive and memory-efficent form, discuss their known convergence properties and illustrate their relative empirical behavior on Garnet problems. Our experiments suggest that the most standard algorithms on and off-policy LSTD(λ)/LSPE(λ) - and TD(λ) if the feature space dimension is too large for a least-squares approach - perform the best.
            """ ;
    dct:identifier "hal-00644516" ;
    dct:issued "2026-05-11T13:09:05.759407"^^xsd:dateTime ;
    dct:language "en" ;
    dct:modified "2026-05-11T13:09:05.759414"^^xsd:dateTime ;
    dct:publisher <https://rec.harvest-normandie.data4citizen.com/organization/cce9db95-46d9-4dc2-84b6-764215d0a002> ;
    dct:title "Off-policy Learning with Eligibility Traces: A Survey" ;
    dcat:contactPoint [ a vcard:Organization ;
            vcard:fn "CCSD" ] ;
    dcat:distribution <https://rec.harvest-normandie.data4citizen.com/dataset/oai-hal-hal-00644516v2/resource/3d58bcc0-1692-497a-af71-3bbc15730d7d> ;
    dcat:keyword "eligibility-traces",
        "infoeu-reposemanticsreport",
        "infoinfo-aicomputer-science-csartificial-intelligence-csai",
        "infoinfo-rocomputer-science-csoperations-research-mathoc",
        "off-policy-learning",
        "reinforcement-learning",
        "reports",
        "value-estimation" ;
    dcat:landingPage <https://inria.hal.science/hal-00644516> .

<https://rec.harvest-normandie.data4citizen.com/dataset/oai-hal-hal-00644516v2/resource/3d58bcc0-1692-497a-af71-3bbc15730d7d> a dcat:Distribution ;
    dct:format "HTML" ;
    dct:issued "2026-05-11T13:09:05.776494"^^xsd:dateTime ;
    dct:modified "2026-05-11T13:09:05.744190"^^xsd:dateTime ;
    dct:title "Off-policy Learning with Eligibility Traces: A Survey" ;
    dcat:accessURL <https://inria.hal.science/hal-00644516> .

<https://rec.harvest-normandie.data4citizen.com/organization/cce9db95-46d9-4dc2-84b6-764215d0a002> a foaf:Agent ;
    foaf:name "test_moissonnage_selune" .

<https://inria.hal.science/hal-00644516> a foaf:Document .