@prefix this: <https://w3id.org/kpxl/ios/ds/np/RAZmAIr2d55irsE4M3hGyMk9UXJqPawb8CU92Xj2Nc3QQ> .
@prefix sub: <https://w3id.org/kpxl/ios/ds/np/RAZmAIr2d55irsE4M3hGyMk9UXJqPawb8CU92Xj2Nc3QQ#> .
@prefix np: <http://www.nanopub.org/nschema#> .
@prefix dct: <http://purl.org/dc/terms/> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix nt: <https://w3id.org/np/o/ntemplate/> .
@prefix npx: <http://purl.org/nanopub/x/> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix orcid: <https://orcid.org/> .
@prefix ns1: <http://purl.org/np/> .
@prefix prov: <http://www.w3.org/ns/prov#> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
sub:Head {
  this: np:hasAssertion sub:assertion ;
    np:hasProvenance sub:provenance ;
    np:hasPublicationInfo sub:pubinfo ;
    a np:Nanopublication .
}
sub:assertion {
  <https://w3id.org/kpxl/ios/ds/terms/SAC-TD3_Hybrid> a <http://www.w3.org/2002/07/owl#Class> ;
    rdfs:label "SAC-TD3 Hybrid" ;
    rdfs:subClassOf <http://www.wikidata.org/entity/Q8366> ;
    <http://www.w3.org/2002/07/owl#sameAs> <https://w3id.org/np/RAgOeYsOZ9JMrf7eZXm9LfwjGMukSuzSpk6eeHFRpRlNo#SAC-TD3Hybrid> ;
    <http://www.w3.org/2004/02/skos/core#definition> "SAC-TD3 is an algorithm incorporating elements both from the SAC and TD3 algorithms for reinforcement learning. It incorporates the idea of entropy regularization from SAC while borrowing target policy smoothening, delayed policy updates from the TD3 algorithm. It has been used to estimate the reaction barrier given a potential energy surface. Stable states in complex systems correspond to local minima on the associated potential energy surface, transitions between which govern the dynamics of the system. Precisely determining the transition pathways in complex and high-dimensional systems is challenging because these transitions are rare events, and the system remains near a local minimum for most of the time. The probability of such transitions decreases exponentially with the height of the energy barrier, making the system's dynamics highly sensitive to the calculated energy barriers. This problem has is formulated as a cost-minimization problem and solved using the aforementioned reinforcement learning algorithm. The exploratory nature of the algorithm enables efficient sampling and better estimation of the minimum energy barrier for transitions." ;
    <http://www.w3.org/2004/02/skos/core#relatedMatch> <http://www.wikidata.org/entity/Q65079156> , <http://www.wikidata.org/entity/Q830687> .
}
sub:provenance {
  <https://doi.org/10.3233/DS-240063> a <http://purl.org/spar/fabio/ScholarlyWork> .
  sub:assertion prov:wasGeneratedBy sub:research-activity .
  sub:research-activity dct:description <https://doi.org/10.3233/DS-240063> .
}
sub:pubinfo {
  <http://www.wikidata.org/entity/Q65079156> nt:hasLabelFromApi "deep reinforcement learning - techniques combining deep learning and reinforcement learning principles to create efficient machine learning algorithms" .
  <http://www.wikidata.org/entity/Q830687> nt:hasLabelFromApi "reinforcement learning - field of machine learning" .
  <http://www.wikidata.org/entity/Q8366> nt:hasLabelFromApi "algorithm - sequence of instructions to perform a task" .
  orcid:0000-0002-1267-0234 foaf:name "Tobias Kuhn" .
  orcid:0009-0005-0705-7768 foaf:name "Adittya Pal" .
  sub:author-list rdf:_1 orcid:0009-0005-0705-7768 .
  sub:sig npx:hasAlgorithm "RSA" ;
    npx:hasPublicKey "MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQD4Wj537OijfOWVtsHMznuXKISqBhtGDQZfdO6pbb4hg9EHMcUFGTLbWaPrP783PHv8HMAAPjvEkHLaOHMIknqhaIa5236lfBO3r+ljVdYBElBcLvROmwG+ZGtmPNZf7lMhI15xf5TfoaSa84AFRd5J2EXekK6PhaFQhRm1IpSYtwIDAQAB" ;
    npx:hasSignature "qBWfuuQ/Z0nFwT/HNBEBhZ5sVgqJOwYnmn0+NRE1PU9+aUMbS2qwWOLTHN+Zt09qythSHJsEUxc1pefwaLY7vIvs02SDI/pTXwu+vcEvx6GFFyLOLJieFN6K3aIlWIi2zEpgRzc3yKt9v6uJzbDZKMagBvyLL1W9489r8802sb0=" ;
    npx:hasSignatureTarget this: ;
    npx:signedBy orcid:0000-0002-1267-0234 .
  this: dct:created "2024-10-04T09:20:40.120Z"^^xsd:dateTime ;
    dct:creator orcid:0000-0002-1267-0234 ;
    dct:isPartOf <https://doi.org/10.3233/DS-240063> ;
    dct:license <https://creativecommons.org/licenses/by/4.0/> ;
    npx:hasNanopubType <https://w3id.org/kpxl/ios/ds/terms/DataScienceNanopub> ;
    npx:introduces <https://w3id.org/kpxl/ios/ds/terms/SAC-TD3_Hybrid> ;
    npx:wasCreatedAt <https://nanodash.knowledgepixels.com/> ;
    <http://purl.org/ontology/bibo/authorList> sub:author-list ;
    a npx:DraftNanopub ;
    rdfs:label "Class: SAC-TD3 Hybrid" ;
    prov:wasDerivedFrom <https://w3id.org/np/RAgOeYsOZ9JMrf7eZXm9LfwjGMukSuzSpk6eeHFRpRlNo> ;
    nt:wasCreatedFromProvenanceTemplate ns1:RAl_-VTw9Re_uRF8r8y0rjlfnu7FlhTa8xg_8xkcweqiE ;
    nt:wasCreatedFromPubinfoTemplate ns1:RAA2MfqdBCzmz9yVWjKLXNbyfBNcwsMmOqcNUxkk1maIM , ns1:RABngHbKpoJ3U9Nebc8mX_KUdv_vXw28EejqAyQya5zVA , ns1:RAbi5DDAdvk1G9P8KsHY_3-hDG6Ev5j0Ax0mKhJuM2gbE , ns1:RAh1gm83JiG5M6kDxXhaYT1l49nCzyrckMvTzcPn-iv90 , <https://w3id.org/np/RA5R_qv3VsZIrDKd8Mr37x3HoKCsKkwN5tJVqgQsKhjTE> , <https://w3id.org/np/RAIabr2sRVJ-YOIwZRD__BVMJKnq3QtQw_mjLIGSACPAI> , <https://w3id.org/np/RA_JdI7pfDcyvEXLr_gper3h8egmNggeTqkJbyHrlMEdo> , <https://w3id.org/np/RAoWx0AJvNw-WqkGgZO4k8udNCg6kMcGZARN3DgO_5TII> ;
    nt:wasCreatedFromTemplate <https://w3id.org/np/RAxfD9wQMHU4DmWta5uRpo723ZgKpizglley4gtcxG0hg> .
}