[ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/Head", "@graph": [ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78", "http://www.nanopub.org/nschema#hasAssertion": [ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/assertion" } ], "http://www.nanopub.org/nschema#hasProvenance": [ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/provenance" } ], "http://www.nanopub.org/nschema#hasPublicationInfo": [ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/pubinfo" } ], "@type": [ "http://www.nanopub.org/nschema#Nanopublication" ] } ] }, { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/provenance", "@graph": [ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/assertion", "http://www.w3.org/ns/prov#wasAttributedTo": [ { "@id": "https://orcid.org/0009-0008-8411-2742" } ] } ] }, { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/pubinfo", "@graph": [ { "@id": "https://orcid.org/0009-0008-8411-2742", "http://xmlns.com/foaf/0.1/name": [ { "@value": "Emily Regalado" } ] }, { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78", "http://purl.org/dc/terms/created": [ { "@value": "2026-04-30T21:39:47.426Z", "@type": "http://www.w3.org/2001/XMLSchema#dateTime" } ], "http://purl.org/dc/terms/creator": [ { "@id": "https://orcid.org/0009-0008-8411-2742" } ], "http://purl.org/dc/terms/license": [ { "@id": "https://creativecommons.org/licenses/by/4.0/" } ], "http://purl.org/nanopub/x/introduces": [ { "@id": "https://doi.org/10.1145/3712256.3726452" } ], "http://purl.org/nanopub/x/wasCreatedAt": [ { "@id": "https://nanodash.knowledgepixels.com/" } ], "https://w3id.org/np/o/ntemplate/wasCreatedFromProvenanceTemplate": [ { "@id": "https://w3id.org/np/RA7lSq6MuK_TIC6JMSHvLtee3lpLoZDOqLJCLXevnrPoU" } ], "https://w3id.org/np/o/ntemplate/wasCreatedFromPubinfoTemplate": [ { "@id": "https://w3id.org/np/RACJ58Gvyn91LqCKIO9zu1eijDQIeEff28iyDrJgjSJF8" }, { "@id": "https://w3id.org/np/RAukAcWHRDlkqxk7H2XNSegc1WnHI569INvNr-xdptDGI" } ], "https://w3id.org/np/o/ntemplate/wasCreatedFromTemplate": [ { "@id": "https://w3id.org/np/RArM5GTwgxg9qslGX-XiQ-KTTUwdoM0KB1YqmT4GqTizA" } ] }, { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/sig", "http://purl.org/nanopub/x/hasAlgorithm": [ { "@value": "RSA" } ], "http://purl.org/nanopub/x/hasPublicKey": [ { "@value": "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAxzr6UBGMW6c8tegz0babaledWUEQ0PLDE4tp7Iinbe2DZtAtY5JUptKYuStWDZx+QER4808P8dejNWRnBDzgthYJm/AyNSXflHSJhz2+NC+h7RylOLxbwLEQocmyKKiYxa2gT85m6ajVL2M6TnfG67nnK+K2f7iCGL6wYXRITD1q+7+5SWqBdDXIV921W4IKWaD2GJk+NRBoOqQhbsrk8Tn5XsNd7DMYVHk47oMDGbeBnrOIoRPsbBgAcoCsxxhiB9yN6Lf8EUbnlXVEDzJuZk048L1BDZL+6nkA8btTQGP2ijUFWA7rTrod3LjUDQWLZS95njjl867dtmv/znYkzwIDAQAB" } ], "http://purl.org/nanopub/x/hasSignature": [ { "@value": "QK0Uq0dM8EDClZWwK1iypzM5Jofx7eS22L4Yyk8y1QSVx7lJke+W4p4J+YgX6SyQ5ArHEcpoJHzdiV/fM2BzLoBO5d4TqI2fXMpyAdEa3MCZBkv2VnG7G27xSBbEEuYQQfKCdCuLpxFTUfq7u6U9225ODch4R53l2xXGGJPhzvwuwAFxphAzJcrDZo8NzhyHbYq3Mp7Y0FZUbbAF6GBwK/qxrRVuUNuhVE6+EMSo9o3cATE/pb5B5YMkOSY2GYfsThybCKX0FETh5T5L8pp4AY3kA8aCW42ZpH0511DkuMpDNvyDArvBmj85jLc7wJaJPV8n2NtpbChXFOrjlMWIug==" } ], "http://purl.org/nanopub/x/hasSignatureTarget": [ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78" } ], "http://purl.org/nanopub/x/signedBy": [ { "@id": "https://orcid.org/0009-0008-8411-2742" } ] } ] }, { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78/assertion", "@graph": [ { "@id": "https://doi.org/10.1145/3712256.3726452", "http://purl.org/dc/terms/creator": [ { "@id": "https://orcid.org/0000-0001-9487-5622" } ], "http://purl.org/dc/terms/publisher": [ { "@id": "https://ror.org/021nxhr62" } ], "http://purl.org/dc/terms/subject": [ { "@id": "http://edamontology.org/topic_3316" } ], "@type": [ "https://w3id.org/fair/ff/terms/article", "https://w3id.org/fdof/ontology#FAIRDigitalObject" ], "http://www.w3.org/2000/01/rdf-schema#comment": [ { "@value": "Ant Colony Optimization (ACO) has served as a widely-utilized metaheuristic algorithm for decades for solving combinatorial optimization problems. Since its initial construction, ACO has seen a wide variety of modifications and connections to Reinforcement Learning (RL). Substantial parallels can be seen as early as 1995 with Ant-Q's relationship with Q-learning, through 2022 with ADACO's connection with Policy Gradient. In this work, we describe ACO, more specifically the Stochastic Gradient Descent ACO algorithm (ACOSGD), explicitly as an off-policy Policy Gradient (PG) method. We also incorporate experience replay into several ACO algorithm variants, including AS, MaxMin-ACO, ACOSGD, ADACO, and our two policy gradient-based versions: PGACO and PPOACO, drawing the connection to elitist ACO strategies. We show that our implementation of PG in ACO with experience replay and a baselined reward update strategy applied to eight TSP problems of varying sizes performs competitively with both fundamental ACO and SGD-based ACO versions. We also show that the replay buffer seems to unilaterally improve the performance of ACO algorithms through an ablation study" } ], "http://www.w3.org/2000/01/rdf-schema#label": [ { "@value": "Ant Colony Optimization with Policy Gradients and Replay" } ], "https://w3id.org/fdof/ontology#hasMetadata": [ { "@id": "https://w3id.org/np/RAbv_E_U02qVYAHDisjKEUhi7qQYFsjhGqL24QEbWRP78" } ], "https://www.w3.org/ns/dcat#contactPoint": [ { "@value": "john.sheppard@montana.edu" } ], "https://www.w3.org/ns/dcat#endDate": [ { "@value": "July 13 2025" } ], "https://www.w3.org/ns/dcat#startDate": [ { "@value": "2024" } ] } ] } ]