{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:K2VFJVOIUXDRUZFJFVCV4MM2ZS","short_pith_number":"pith:K2VFJVOI","schema_version":"1.0","canonical_sha256":"56aa54d5c8a5c71a64a92d455e319acc8a5559891b1bcf13d708be660cf7fefe","source":{"kind":"arxiv","id":"1802.04240","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Solving the Vehicle Routing Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Afshin Oroojlooy, Lawrence V. Snyder, Martin Tak\\'a\\v{c}, Mohammadreza Nazari","submitted_at":"2018-02-12T18:41:57Z","abstract_excerpt":"We present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using reinforcement learning. In this approach, we train a single model that finds near-optimal solutions for problem instances sampled from a given distribution, only by observing the reward signals and following feasibility rules. Our model represents a parameterized stochastic policy, and by applying a policy gradient algorithm to optimize its parameters, the trained model produces the solution as a sequence of consecutive actions in real time, without the need to re-train for every new problem instance. On cap"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.04240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T18:41:57Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"40cfa38764549ca05164b27d4c4ee87b2e5f0cc6ac5eba217ed49a8695e67f69","abstract_canon_sha256":"e32f3f57a4673265bc95f62c42b86b911a5e14023a12946797ad4f5db36607e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:28.113785Z","signature_b64":"QzCsXdyFTe+HRhdDyFkpHJ+XMGOZIJOSxkcrcNb5RR/R1fR3v/wEILeJ2IRsEQL8KYJEjG2yEYdTmeHqU8iIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56aa54d5c8a5c71a64a92d455e319acc8a5559891b1bcf13d708be660cf7fefe","last_reissued_at":"2026-05-18T00:15:28.113039Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:28.113039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Solving the Vehicle Routing Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Afshin Oroojlooy, Lawrence V. Snyder, Martin Tak\\'a\\v{c}, Mohammadreza Nazari","submitted_at":"2018-02-12T18:41:57Z","abstract_excerpt":"We present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using reinforcement learning. In this approach, we train a single model that finds near-optimal solutions for problem instances sampled from a given distribution, only by observing the reward signals and following feasibility rules. Our model represents a parameterized stochastic policy, and by applying a policy gradient algorithm to optimize its parameters, the trained model produces the solution as a sequence of consecutive actions in real time, without the need to re-train for every new problem instance. On cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04240","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.04240","created_at":"2026-05-18T00:15:28.113136+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04240v2","created_at":"2026-05-18T00:15:28.113136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04240","created_at":"2026-05-18T00:15:28.113136+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2VFJVOIUXDR","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2VFJVOIUXDRUZFJ","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2VFJVOI","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26566","citing_title":"Learning to Route Electric Trucks Under Operational Uncertainty","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS","json":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS.json","graph_json":"https://pith.science/api/pith-number/K2VFJVOIUXDRUZFJFVCV4MM2ZS/graph.json","events_json":"https://pith.science/api/pith-number/K2VFJVOIUXDRUZFJFVCV4MM2ZS/events.json","paper":"https://pith.science/paper/K2VFJVOI"},"agent_actions":{"view_html":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS","download_json":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS.json","view_paper":"https://pith.science/paper/K2VFJVOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04240&json=true","fetch_graph":"https://pith.science/api/pith-number/K2VFJVOIUXDRUZFJFVCV4MM2ZS/graph.json","fetch_events":"https://pith.science/api/pith-number/K2VFJVOIUXDRUZFJFVCV4MM2ZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS/action/storage_attestation","attest_author":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS/action/author_attestation","sign_citation":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS/action/citation_signature","submit_replication":"https://pith.science/pith/K2VFJVOIUXDRUZFJFVCV4MM2ZS/action/replication_record"}},"created_at":"2026-05-18T00:15:28.113136+00:00","updated_at":"2026-05-18T00:15:28.113136+00:00"}