{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:47KLRIIMQU7ARRLGDWKI6WNDAT","short_pith_number":"pith:47KLRIIM","schema_version":"1.0","canonical_sha256":"e7d4b8a10c853e08c5661d948f59a304e850fec76c6c4188908de7c44e5745ac","source":{"kind":"arxiv","id":"1907.04484","version":1},"attestation_state":"computed","paper":{"title":"Co-training for Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jialin Song, Masahiro Ono, Ravi Lanka, Yisong Yue","submitted_at":"2019-07-03T02:54:13Z","abstract_excerpt":"We study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as planning (e.g., multiple integer programming formulations) and various combinatorial optimization problems (e.g., those with both integer programming and graph-based formulations). Inspired by the classical co-training framework for classification, we study the problem of co-training for policy learning. We present sufficient conditions under which learning from two views can improve upon learning from a single view "},"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":"1907.04484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T02:54:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3bfe9cb98854467b9fb25ef57341930c9a18acbf7348aa2c6779c36f5d75c6e1","abstract_canon_sha256":"88a0a12a77f723ace2e191907a5b6f2215fc88d75cb488a60c09d931f520bfe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:00.145290Z","signature_b64":"wqadMML/CBkktopcQ+2S1yNrIHjoP9cIvBwQqck/Yy8HBsTQDsnAS0dTqlqeO6/TFDn+l+K1mDZqHqUFF2J1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7d4b8a10c853e08c5661d948f59a304e850fec76c6c4188908de7c44e5745ac","last_reissued_at":"2026-05-17T23:41:00.144715Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:00.144715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-training for Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jialin Song, Masahiro Ono, Ravi Lanka, Yisong Yue","submitted_at":"2019-07-03T02:54:13Z","abstract_excerpt":"We study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as planning (e.g., multiple integer programming formulations) and various combinatorial optimization problems (e.g., those with both integer programming and graph-based formulations). Inspired by the classical co-training framework for classification, we study the problem of co-training for policy learning. We present sufficient conditions under which learning from two views can improve upon learning from a single view "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04484","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":""},"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":"1907.04484","created_at":"2026-05-17T23:41:00.144817+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04484v1","created_at":"2026-05-17T23:41:00.144817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04484","created_at":"2026-05-17T23:41:00.144817+00:00"},{"alias_kind":"pith_short_12","alias_value":"47KLRIIMQU7A","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"47KLRIIMQU7ARRLG","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"47KLRIIM","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT","json":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT.json","graph_json":"https://pith.science/api/pith-number/47KLRIIMQU7ARRLGDWKI6WNDAT/graph.json","events_json":"https://pith.science/api/pith-number/47KLRIIMQU7ARRLGDWKI6WNDAT/events.json","paper":"https://pith.science/paper/47KLRIIM"},"agent_actions":{"view_html":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT","download_json":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT.json","view_paper":"https://pith.science/paper/47KLRIIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04484&json=true","fetch_graph":"https://pith.science/api/pith-number/47KLRIIMQU7ARRLGDWKI6WNDAT/graph.json","fetch_events":"https://pith.science/api/pith-number/47KLRIIMQU7ARRLGDWKI6WNDAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/action/storage_attestation","attest_author":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/action/author_attestation","sign_citation":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/action/citation_signature","submit_replication":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/action/replication_record"}},"created_at":"2026-05-17T23:41:00.144817+00:00","updated_at":"2026-05-17T23:41:00.144817+00:00"}