{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:5CMLYQDZCWE4KRXTTF3OSKTLCN","short_pith_number":"pith:5CMLYQDZ","schema_version":"1.0","canonical_sha256":"e898bc40791589c546f39976e92a6b136133bbdc9e8fd859f7fce1c08e96f2e1","source":{"kind":"arxiv","id":"1301.2343","version":1},"attestation_state":"computed","paper":{"title":"Planning by Prioritized Sweeping with Small Backups","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Harm van Seijen, Richard S. Sutton","submitted_at":"2013-01-10T21:54:42Z","abstract_excerpt":"Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibi"},"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":"1301.2343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-10T21:54:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff487f7a5c36fa92bb1494e6f0c33996af262dfcfa40ef4595538cfa26d9351f","abstract_canon_sha256":"11378e2b8615b107b6108658c8b3d70761c420c4cb0e62aa331f5d9b8ff49f05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:45.273695Z","signature_b64":"wS+WV1ysH091uStRfa7Kx0ay+p2ApOgsRxnTtylEf0q4WxjlOhPaLzw9Qr8/d5117CVVdY0J1BzH+Fpq8ijQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e898bc40791589c546f39976e92a6b136133bbdc9e8fd859f7fce1c08e96f2e1","last_reissued_at":"2026-05-18T03:36:45.273055Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:45.273055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Planning by Prioritized Sweeping with Small Backups","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Harm van Seijen, Richard S. Sutton","submitted_at":"2013-01-10T21:54:42Z","abstract_excerpt":"Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.2343","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":"1301.2343","created_at":"2026-05-18T03:36:45.273138+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.2343v1","created_at":"2026-05-18T03:36:45.273138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.2343","created_at":"2026-05-18T03:36:45.273138+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CMLYQDZCWE4","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CMLYQDZCWE4KRXT","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CMLYQDZ","created_at":"2026-05-18T12:27:34.582898+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/5CMLYQDZCWE4KRXTTF3OSKTLCN","json":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN.json","graph_json":"https://pith.science/api/pith-number/5CMLYQDZCWE4KRXTTF3OSKTLCN/graph.json","events_json":"https://pith.science/api/pith-number/5CMLYQDZCWE4KRXTTF3OSKTLCN/events.json","paper":"https://pith.science/paper/5CMLYQDZ"},"agent_actions":{"view_html":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN","download_json":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN.json","view_paper":"https://pith.science/paper/5CMLYQDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.2343&json=true","fetch_graph":"https://pith.science/api/pith-number/5CMLYQDZCWE4KRXTTF3OSKTLCN/graph.json","fetch_events":"https://pith.science/api/pith-number/5CMLYQDZCWE4KRXTTF3OSKTLCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/action/storage_attestation","attest_author":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/action/author_attestation","sign_citation":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/action/citation_signature","submit_replication":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/action/replication_record"}},"created_at":"2026-05-18T03:36:45.273138+00:00","updated_at":"2026-05-18T03:36:45.273138+00:00"}