{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:K2VFJVOIUXDRUZFJFVCV4MM2ZS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e32f3f57a4673265bc95f62c42b86b911a5e14023a12946797ad4f5db36607e8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T18:41:57Z","title_canon_sha256":"40cfa38764549ca05164b27d4c4ee87b2e5f0cc6ac5eba217ed49a8695e67f69"},"schema_version":"1.0","source":{"id":"1802.04240","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04240","created_at":"2026-05-18T00:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04240v2","created_at":"2026-05-18T00:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04240","created_at":"2026-05-18T00:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"K2VFJVOIUXDR","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K2VFJVOIUXDRUZFJ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K2VFJVOI","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:a64297bd5365677059b1364bf04ff03877d2b29adb8cd75749af188c043397f9","target":"graph","created_at":"2026-05-18T00:15:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Afshin Oroojlooy, Lawrence V. Snyder, Martin Tak\\'a\\v{c}, Mohammadreza Nazari","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T18:41:57Z","title":"Reinforcement Learning for Solving the Vehicle Routing Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04240","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eed8ec9d2d033b67a96e344e1a1bbfca86f2ac4eae36b8d5a45a439d0eaab4eb","target":"record","created_at":"2026-05-18T00:15:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e32f3f57a4673265bc95f62c42b86b911a5e14023a12946797ad4f5db36607e8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T18:41:57Z","title_canon_sha256":"40cfa38764549ca05164b27d4c4ee87b2e5f0cc6ac5eba217ed49a8695e67f69"},"schema_version":"1.0","source":{"id":"1802.04240","kind":"arxiv","version":2}},"canonical_sha256":"56aa54d5c8a5c71a64a92d455e319acc8a5559891b1bcf13d708be660cf7fefe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56aa54d5c8a5c71a64a92d455e319acc8a5559891b1bcf13d708be660cf7fefe","first_computed_at":"2026-05-18T00:15:28.113039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:28.113039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QzCsXdyFTe+HRhdDyFkpHJ+XMGOZIJOSxkcrcNb5RR/R1fR3v/wEILeJ2IRsEQL8KYJEjG2yEYdTmeHqU8iIBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:28.113785Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04240","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eed8ec9d2d033b67a96e344e1a1bbfca86f2ac4eae36b8d5a45a439d0eaab4eb","sha256:a64297bd5365677059b1364bf04ff03877d2b29adb8cd75749af188c043397f9"],"state_sha256":"1290a95c294e4244c0ab421a8f2948d9d440c6477c483851fcacc5bfb399889b"}