{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XS5XNAH62L6MLX2UZLIA457AHR","short_pith_number":"pith:XS5XNAH6","schema_version":"1.0","canonical_sha256":"bcbb7680fed2fcc5df54cad00e77e03c52d6eb5b2f68d9091581f27e0acc4aab","source":{"kind":"arxiv","id":"2010.12001","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Delarue, Christian Tjandraatmadja, Ross Anderson","submitted_at":"2020-10-22T19:32:21Z","abstract_excerpt":"Value-function-based methods have long played an important role in reinforcement learning. However, finding the best next action given a value function of arbitrary complexity is nontrivial when the action space is too large for enumeration. We develop a framework for value-function-based deep reinforcement learning with a combinatorial action space, in which the action selection problem is explicitly formulated as a mixed-integer optimization problem. As a motivating example, we present an application of this framework to the capacitated vehicle routing problem (CVRP), a combinatorial optimiz"},"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":"2010.12001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T19:32:21Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"1841bf87b9a427436686273b9fe3e280ac08c47c4729bf7150e5cceebeb8361a","abstract_canon_sha256":"ef548c34068b1595a16c6a4a3561a8b269065428325396b0bb3adf85a3f5e3b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:32.584620Z","signature_b64":"clI7YqcFfPK+kmz1m6AusKRywIW3cIGkOmr52w1C9eMwmMwUNZU1yb3OME6RiHYBiC8XVqNzkKNx8s28bQczDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcbb7680fed2fcc5df54cad00e77e03c52d6eb5b2f68d9091581f27e0acc4aab","last_reissued_at":"2026-07-05T01:45:32.584127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:32.584127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Delarue, Christian Tjandraatmadja, Ross Anderson","submitted_at":"2020-10-22T19:32:21Z","abstract_excerpt":"Value-function-based methods have long played an important role in reinforcement learning. However, finding the best next action given a value function of arbitrary complexity is nontrivial when the action space is too large for enumeration. We develop a framework for value-function-based deep reinforcement learning with a combinatorial action space, in which the action selection problem is explicitly formulated as a mixed-integer optimization problem. As a motivating example, we present an application of this framework to the capacitated vehicle routing problem (CVRP), a combinatorial optimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12001","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.12001/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2010.12001","created_at":"2026-07-05T01:45:32.584182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12001v1","created_at":"2026-07-05T01:45:32.584182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12001","created_at":"2026-07-05T01:45:32.584182+00:00"},{"alias_kind":"pith_short_12","alias_value":"XS5XNAH62L6M","created_at":"2026-07-05T01:45:32.584182+00:00"},{"alias_kind":"pith_short_16","alias_value":"XS5XNAH62L6MLX2U","created_at":"2026-07-05T01:45:32.584182+00:00"},{"alias_kind":"pith_short_8","alias_value":"XS5XNAH6","created_at":"2026-07-05T01:45:32.584182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02712","citing_title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR","json":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR.json","graph_json":"https://pith.science/api/pith-number/XS5XNAH62L6MLX2UZLIA457AHR/graph.json","events_json":"https://pith.science/api/pith-number/XS5XNAH62L6MLX2UZLIA457AHR/events.json","paper":"https://pith.science/paper/XS5XNAH6"},"agent_actions":{"view_html":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR","download_json":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR.json","view_paper":"https://pith.science/paper/XS5XNAH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12001&json=true","fetch_graph":"https://pith.science/api/pith-number/XS5XNAH62L6MLX2UZLIA457AHR/graph.json","fetch_events":"https://pith.science/api/pith-number/XS5XNAH62L6MLX2UZLIA457AHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR/action/storage_attestation","attest_author":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR/action/author_attestation","sign_citation":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR/action/citation_signature","submit_replication":"https://pith.science/pith/XS5XNAH62L6MLX2UZLIA457AHR/action/replication_record"}},"created_at":"2026-07-05T01:45:32.584182+00:00","updated_at":"2026-07-05T01:45:32.584182+00:00"}