{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FEL45FVFDJ3STAZUBQ57QKW7IW","short_pith_number":"pith:FEL45FVF","schema_version":"1.0","canonical_sha256":"2917ce96a51a772983340c3bf82adf45b05e4aac1937a39e6fd38869d9aba1c0","source":{"kind":"arxiv","id":"1907.08461","version":1},"attestation_state":"computed","paper":{"title":"Delegative Reinforcement Learning: learning to avoid traps with a little help","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Vanessa Kosoy","submitted_at":"2019-07-19T11:19:03Z","abstract_excerpt":"Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an external advisor. We thus arrive at a setting of active one-shot model-based reinforcement learning that we call DRL (delegative reinforcement learning.) The algorithm we construct in order to demonstrate the regret bound is a variant of Posterior Sampling Reinforcement Learning supplemented by a subroutine that decides which actions should be delegated. The a"},"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":"1907.08461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-19T11:19:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3602d281966a75c84d7533408ba12f4f8bc3fdcfb94547db999866a9a74f7022","abstract_canon_sha256":"089c4adde0c5a63dce56f31c1713364b0b9cf93c523d2e6fbd3d6e8beed77332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:09.753601Z","signature_b64":"9jqFDsZz3QiCVEmtTy32PRRfPFIN3IoPRx1hKmvNmWbvWAq8zwqI8nCx6fX5glNdO0gpdw0igWLmL0aIFR5AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2917ce96a51a772983340c3bf82adf45b05e4aac1937a39e6fd38869d9aba1c0","last_reissued_at":"2026-05-17T23:40:09.753053Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:09.753053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delegative Reinforcement Learning: learning to avoid traps with a little help","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Vanessa Kosoy","submitted_at":"2019-07-19T11:19:03Z","abstract_excerpt":"Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an external advisor. We thus arrive at a setting of active one-shot model-based reinforcement learning that we call DRL (delegative reinforcement learning.) The algorithm we construct in order to demonstrate the regret bound is a variant of Posterior Sampling Reinforcement Learning supplemented by a subroutine that decides which actions should be delegated. The a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08461","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":"1907.08461","created_at":"2026-05-17T23:40:09.753144+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.08461v1","created_at":"2026-05-17T23:40:09.753144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08461","created_at":"2026-05-17T23:40:09.753144+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEL45FVFDJ3S","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEL45FVFDJ3STAZU","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEL45FVF","created_at":"2026-05-18T12:33:15.570797+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/FEL45FVFDJ3STAZUBQ57QKW7IW","json":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW.json","graph_json":"https://pith.science/api/pith-number/FEL45FVFDJ3STAZUBQ57QKW7IW/graph.json","events_json":"https://pith.science/api/pith-number/FEL45FVFDJ3STAZUBQ57QKW7IW/events.json","paper":"https://pith.science/paper/FEL45FVF"},"agent_actions":{"view_html":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW","download_json":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW.json","view_paper":"https://pith.science/paper/FEL45FVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.08461&json=true","fetch_graph":"https://pith.science/api/pith-number/FEL45FVFDJ3STAZUBQ57QKW7IW/graph.json","fetch_events":"https://pith.science/api/pith-number/FEL45FVFDJ3STAZUBQ57QKW7IW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW/action/storage_attestation","attest_author":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW/action/author_attestation","sign_citation":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW/action/citation_signature","submit_replication":"https://pith.science/pith/FEL45FVFDJ3STAZUBQ57QKW7IW/action/replication_record"}},"created_at":"2026-05-17T23:40:09.753144+00:00","updated_at":"2026-05-17T23:40:09.753144+00:00"}