{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CDTHA7PCHT2QYOJYXHAAULO6W2","short_pith_number":"pith:CDTHA7PC","schema_version":"1.0","canonical_sha256":"10e6707de23cf50c3938b9c00a2ddeb6abd65f904c8d5164f6e00d0b70865e31","source":{"kind":"arxiv","id":"2210.15755","version":1},"attestation_state":"computed","paper":{"title":"Confident Approximate Policy Iteration for Efficient Local Planning in $q^\\pi$-realizable MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Gell\\'ert Weisz, Tadashi Kozuno","submitted_at":"2022-10-27T20:19:31Z","abstract_excerpt":"We consider approximate dynamic programming in $\\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy Iteration (API), called Confident Approximate Policy Iteration (CAPI), which computes a deterministic stationary policy with an optimal error bound scaling linearly with the product of the effective horizon $H$ and the worst-case approximation error $\\epsilon$ of the action-value functions of stationary policies. This improvement over API (whose error scales with "},"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":"2210.15755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-27T20:19:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b10a881b71b1b3859e9597abc17524c82297995417774f01a11cb7ffac9e8bf1","abstract_canon_sha256":"d49361c5ef27602cff6298c94ce3169a54070c4000fcef59765746149f1d8c4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:10.526141Z","signature_b64":"+7Jwl+iCYXooX0A0u3dpUTCvYjx9Mxm1uxGk7chJXZmXYR8Y4fPo/x4hZuJwTwp98LUboWQmfxzAo8db7tDPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10e6707de23cf50c3938b9c00a2ddeb6abd65f904c8d5164f6e00d0b70865e31","last_reissued_at":"2026-07-05T05:11:10.525670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:10.525670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confident Approximate Policy Iteration for Efficient Local Planning in $q^\\pi$-realizable MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Gell\\'ert Weisz, Tadashi Kozuno","submitted_at":"2022-10-27T20:19:31Z","abstract_excerpt":"We consider approximate dynamic programming in $\\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy Iteration (API), called Confident Approximate Policy Iteration (CAPI), which computes a deterministic stationary policy with an optimal error bound scaling linearly with the product of the effective horizon $H$ and the worst-case approximation error $\\epsilon$ of the action-value functions of stationary policies. This improvement over API (whose error scales with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15755","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/2210.15755/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":"2210.15755","created_at":"2026-07-05T05:11:10.525730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15755v1","created_at":"2026-07-05T05:11:10.525730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15755","created_at":"2026-07-05T05:11:10.525730+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDTHA7PCHT2Q","created_at":"2026-07-05T05:11:10.525730+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDTHA7PCHT2QYOJY","created_at":"2026-07-05T05:11:10.525730+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDTHA7PC","created_at":"2026-07-05T05:11:10.525730+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/CDTHA7PCHT2QYOJYXHAAULO6W2","json":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2.json","graph_json":"https://pith.science/api/pith-number/CDTHA7PCHT2QYOJYXHAAULO6W2/graph.json","events_json":"https://pith.science/api/pith-number/CDTHA7PCHT2QYOJYXHAAULO6W2/events.json","paper":"https://pith.science/paper/CDTHA7PC"},"agent_actions":{"view_html":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2","download_json":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2.json","view_paper":"https://pith.science/paper/CDTHA7PC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15755&json=true","fetch_graph":"https://pith.science/api/pith-number/CDTHA7PCHT2QYOJYXHAAULO6W2/graph.json","fetch_events":"https://pith.science/api/pith-number/CDTHA7PCHT2QYOJYXHAAULO6W2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/action/storage_attestation","attest_author":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/action/author_attestation","sign_citation":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/action/citation_signature","submit_replication":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/action/replication_record"}},"created_at":"2026-07-05T05:11:10.525730+00:00","updated_at":"2026-07-05T05:11:10.525730+00:00"}