[ {
  "@graph" : [ {
    "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk",
    "@type" : [ "http://www.nanopub.org/nschema#Nanopublication" ],
    "http://www.nanopub.org/nschema#hasAssertion" : [ {
      "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#assertion"
    } ],
    "http://www.nanopub.org/nschema#hasProvenance" : [ {
      "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#provenance"
    } ],
    "http://www.nanopub.org/nschema#hasPublicationInfo" : [ {
      "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#pubinfo"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#Head"
}, {
  "@graph" : [ {
    "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#SAC-TD3Hybrid",
    "@type" : [ "http://www.w3.org/2002/07/owl#Class" ],
    "http://www.w3.org/2000/01/rdf-schema#label" : [ {
      "@value" : "a version of the Soft Actor Critic algorithm for reinforcement learning incorporating elements from the TD3 algorithm"
    } ],
    "http://www.w3.org/2000/01/rdf-schema#subClassOf" : [ {
      "@id" : "http://www.wikidata.org/entity/Q8366"
    } ],
    "http://www.w3.org/2004/02/skos/core#definition" : [ {
      "@value" : "SAC-TD3 is an algorithm which 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 a reinforcement learning algorithm which is a hybrid of the existing SAC and TD3 algorithms. It incorporates the idea of entropy regularization from SAC while borrowing target policy smoothening, delayed policy updates from the TD3 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" : [ {
      "@id" : "http://www.wikidata.org/entity/Q830687"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#assertion"
}, {
  "@graph" : [ {
    "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#assertion",
    "http://www.w3.org/ns/prov#wasGeneratedBy" : [ {
      "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#research-activity"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#document",
    "@type" : [ "http://purl.org/ontology/bibo/Manuscript" ]
  }, {
    "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#research-activity",
    "http://purl.org/dc/terms/description" : [ {
      "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#document"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#provenance"
}, {
  "@graph" : [ {
    "@id" : "http://www.wikidata.org/entity/Q830687",
    "https://w3id.org/np/o/ntemplate/hasLabelFromApi" : [ {
      "@value" : "reinforcement learning - field of machine learning"
    } ]
  }, {
    "@id" : "http://www.wikidata.org/entity/Q8366",
    "https://w3id.org/np/o/ntemplate/hasLabelFromApi" : [ {
      "@value" : "algorithm - sequence of instructions to perform a task"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk",
    "@type" : [ "http://purl.org/nanopub/x/DraftNanopub" ],
    "http://purl.org/dc/terms/created" : [ {
      "@type" : "http://www.w3.org/2001/XMLSchema#dateTime",
      "@value" : "2024-09-30T09:16:52.891Z"
    } ],
    "http://purl.org/dc/terms/creator" : [ {
      "@id" : "https://orcid.org/0009-0005-0705-7768"
    } ],
    "http://purl.org/dc/terms/license" : [ {
      "@id" : "https://creativecommons.org/licenses/by/4.0/"
    } ],
    "http://purl.org/nanopub/x/introduces" : [ {
      "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#SAC-TD3Hybrid"
    } ],
    "http://purl.org/nanopub/x/wasCreatedAt" : [ {
      "@id" : "https://nanodash.knowledgepixels.com/"
    } ],
    "http://www.w3.org/2000/01/rdf-schema#label" : [ {
      "@value" : "Class: a version of the Soft Actor Critic algorithm for reinforcement learning incorporating elements fr..."
    } ],
    "http://www.w3.org/ns/prov#wasDerivedFrom" : [ {
      "@id" : "https://w3id.org/np/RA0JAKZR_z1jwkGeEVFh4rApkHM8CDGX2PJqXSpty3iKM"
    } ],
    "https://w3id.org/np/o/ntemplate/wasCreatedFromProvenanceTemplate" : [ {
      "@id" : "http://purl.org/np/RA4LGtuOqTIMqVAkjnfBXk1YDcAPNadP5CGiaJiBkdHCQ"
    } ],
    "https://w3id.org/np/o/ntemplate/wasCreatedFromPubinfoTemplate" : [ {
      "@id" : "http://purl.org/np/RAA2MfqdBCzmz9yVWjKLXNbyfBNcwsMmOqcNUxkk1maIM"
    }, {
      "@id" : "http://purl.org/np/RABngHbKpoJ3U9Nebc8mX_KUdv_vXw28EejqAyQya5zVA"
    }, {
      "@id" : "http://purl.org/np/RAbi5DDAdvk1G9P8KsHY_3-hDG6Ev5j0Ax0mKhJuM2gbE"
    }, {
      "@id" : "http://purl.org/np/RAh1gm83JiG5M6kDxXhaYT1l49nCzyrckMvTzcPn-iv90"
    } ],
    "https://w3id.org/np/o/ntemplate/wasCreatedFromTemplate" : [ {
      "@id" : "https://w3id.org/np/RAxfD9wQMHU4DmWta5uRpo723ZgKpizglley4gtcxG0hg"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#sig",
    "http://purl.org/nanopub/x/hasAlgorithm" : [ {
      "@value" : "RSA"
    } ],
    "http://purl.org/nanopub/x/hasPublicKey" : [ {
      "@value" : "MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCgf5e4OjFQxWlVxXTS0fn6d6Bs2sjO0XW9AIzKzz3I5q9i4eZQWoMYrCtjxsGc+bjyf0+gGfOH0GPt6SgKJf7tkjS67BheM2uEAeB6ryPO77TTZUUanMSuUvdD/jMR1pFeO2CgE/9O0oeI+hxer5upIw43wcdnsuJfeDFnO1204QIDAQAB"
    } ],
    "http://purl.org/nanopub/x/hasSignature" : [ {
      "@value" : "Vz9sb5ruCwuTP1WYDOOU7snpKxc9jEM9Ptg4A3fu61iVNIR/LOJWTtpAxT7Q47gmGHT+0MpKtP4h4LA/X/Tz+pqWPvg680jmXuyy9tutmSOiYZ+WxXrmNIJMZPQbiXy8+H69K5ps9Kxdw4JxKxvIrxdF+IQXB0dC4GURlXnsLzU="
    } ],
    "http://purl.org/nanopub/x/hasSignatureTarget" : [ {
      "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk"
    } ],
    "http://purl.org/nanopub/x/signedBy" : [ {
      "@id" : "https://orcid.org/0009-0005-0705-7768"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RAZdadPk2Lz1Bo6jvZxCeFME9-Yr-NXwBxOJuOxgWfVSk#pubinfo"
} ]