{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RZSIF2HMB3I5N7YJ5YGHLKEFQJ","short_pith_number":"pith:RZSIF2HM","schema_version":"1.0","canonical_sha256":"8e6482e8ec0ed1d6ff09ee0c75a885827e2b30c93449704c9b098d5ba4a21fa9","source":{"kind":"arxiv","id":"2310.01569","version":2},"attestation_state":"computed","paper":{"title":"Iterative Option Discovery for Planning, by Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Kenny Young, Richard S. Sutton","submitted_at":"2023-10-02T19:03:30Z","abstract_excerpt":"Discovering useful temporal abstractions, in the form of options, is widely thought to be key to applying reinforcement learning and planning to increasingly complex domains. Building on the empirical success of the Expert Iteration approach to policy learning used in AlphaZero, we propose Option Iteration, an analogous approach to option discovery. Rather than learning a single strong policy that is trained to match the search results everywhere, Option Iteration learns a set of option policies trained such that for each state encountered, at least one policy in the set matches the search res"},"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":"2310.01569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-02T19:03:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fade54d1b07b2006f574f5a54e1b647587e04b5b56b02485e0f7775179a5f93","abstract_canon_sha256":"4c53852685be4084df567c11e01c0e30ae5cc4625dbd0e9bbd731850c241dc2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:27.038106Z","signature_b64":"VoxNJiNn/TO84vbLSQBROLxOn3k0BywvuFO5gUbnIurf+zh6L+9UOSxsZAcOburEPc1FMaXqqt0PAF7tNqGyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e6482e8ec0ed1d6ff09ee0c75a885827e2b30c93449704c9b098d5ba4a21fa9","last_reissued_at":"2026-07-05T07:27:27.037564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:27.037564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Option Discovery for Planning, by Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Kenny Young, Richard S. Sutton","submitted_at":"2023-10-02T19:03:30Z","abstract_excerpt":"Discovering useful temporal abstractions, in the form of options, is widely thought to be key to applying reinforcement learning and planning to increasingly complex domains. Building on the empirical success of the Expert Iteration approach to policy learning used in AlphaZero, we propose Option Iteration, an analogous approach to option discovery. Rather than learning a single strong policy that is trained to match the search results everywhere, Option Iteration learns a set of option policies trained such that for each state encountered, at least one policy in the set matches the search res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01569","kind":"arxiv","version":2},"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/2310.01569/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":"2310.01569","created_at":"2026-07-05T07:27:27.037631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01569v2","created_at":"2026-07-05T07:27:27.037631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01569","created_at":"2026-07-05T07:27:27.037631+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZSIF2HMB3I5","created_at":"2026-07-05T07:27:27.037631+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZSIF2HMB3I5N7YJ","created_at":"2026-07-05T07:27:27.037631+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZSIF2HM","created_at":"2026-07-05T07:27:27.037631+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/RZSIF2HMB3I5N7YJ5YGHLKEFQJ","json":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ.json","graph_json":"https://pith.science/api/pith-number/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/graph.json","events_json":"https://pith.science/api/pith-number/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/events.json","paper":"https://pith.science/paper/RZSIF2HM"},"agent_actions":{"view_html":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ","download_json":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ.json","view_paper":"https://pith.science/paper/RZSIF2HM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01569&json=true","fetch_graph":"https://pith.science/api/pith-number/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/action/storage_attestation","attest_author":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/action/author_attestation","sign_citation":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/action/citation_signature","submit_replication":"https://pith.science/pith/RZSIF2HMB3I5N7YJ5YGHLKEFQJ/action/replication_record"}},"created_at":"2026-07-05T07:27:27.037631+00:00","updated_at":"2026-07-05T07:27:27.037631+00:00"}