{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FIBCI6LT5JRXA3F7W42UZBHZYV","short_pith_number":"pith:FIBCI6LT","schema_version":"1.0","canonical_sha256":"2a02247973ea63706cbfb7354c84f9c5478ec9df01cfb14d1e794aaf1ac96085","source":{"kind":"arxiv","id":"2404.06136","version":1},"attestation_state":"computed","paper":{"title":"Inexact Policy Iteration Methods for Large-Scale Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dominic Liao-McPherson, Efe Balta, John Lygeros, Matilde Gargiani, Robin Sieber","submitted_at":"2024-04-09T09:03:06Z","abstract_excerpt":"We consider inexact policy iteration methods for large-scale infinite-horizon discounted MDPs with finite spaces, a variant of policy iteration where the policy evaluation step is implemented inexactly using an iterative solver for linear systems. In the classical dynamic programming literature, a similar principle is deployed in optimistic policy iteration, where an a-priori fixed-number of iterations of value iteration is used to inexactly solve the policy evaluation step. Inspired by the connection between policy iteration and semismooth Newton's method, we investigate a class of iPI method"},"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":"2404.06136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-09T09:03:06Z","cross_cats_sorted":[],"title_canon_sha256":"a58294986390d57428fae09d70f1716762dfbd9519e7307c564e4fff8736b3eb","abstract_canon_sha256":"ca9eeea99c4f5dbb171de0a6c2d78f97e19704201716a5ae9f44636d16028904"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:04.676238Z","signature_b64":"HCpr5QEMqGHMuTdvS1dVxTsMIeIsrvX8E/1v1ZWGHtK7wvpDGv4F4KptbiVdvJ+Nqylh6ULCrT109y4ohnWFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a02247973ea63706cbfb7354c84f9c5478ec9df01cfb14d1e794aaf1ac96085","last_reissued_at":"2026-07-05T08:06:04.675728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:04.675728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inexact Policy Iteration Methods for Large-Scale Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dominic Liao-McPherson, Efe Balta, John Lygeros, Matilde Gargiani, Robin Sieber","submitted_at":"2024-04-09T09:03:06Z","abstract_excerpt":"We consider inexact policy iteration methods for large-scale infinite-horizon discounted MDPs with finite spaces, a variant of policy iteration where the policy evaluation step is implemented inexactly using an iterative solver for linear systems. In the classical dynamic programming literature, a similar principle is deployed in optimistic policy iteration, where an a-priori fixed-number of iterations of value iteration is used to inexactly solve the policy evaluation step. Inspired by the connection between policy iteration and semismooth Newton's method, we investigate a class of iPI method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06136","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/2404.06136/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":"2404.06136","created_at":"2026-07-05T08:06:04.675793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06136v1","created_at":"2026-07-05T08:06:04.675793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06136","created_at":"2026-07-05T08:06:04.675793+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIBCI6LT5JRX","created_at":"2026-07-05T08:06:04.675793+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIBCI6LT5JRXA3F7","created_at":"2026-07-05T08:06:04.675793+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIBCI6LT","created_at":"2026-07-05T08:06:04.675793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22538","citing_title":"Inside madupite: Technical Design and Performance","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV","json":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV.json","graph_json":"https://pith.science/api/pith-number/FIBCI6LT5JRXA3F7W42UZBHZYV/graph.json","events_json":"https://pith.science/api/pith-number/FIBCI6LT5JRXA3F7W42UZBHZYV/events.json","paper":"https://pith.science/paper/FIBCI6LT"},"agent_actions":{"view_html":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV","download_json":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV.json","view_paper":"https://pith.science/paper/FIBCI6LT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06136&json=true","fetch_graph":"https://pith.science/api/pith-number/FIBCI6LT5JRXA3F7W42UZBHZYV/graph.json","fetch_events":"https://pith.science/api/pith-number/FIBCI6LT5JRXA3F7W42UZBHZYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV/action/storage_attestation","attest_author":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV/action/author_attestation","sign_citation":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV/action/citation_signature","submit_replication":"https://pith.science/pith/FIBCI6LT5JRXA3F7W42UZBHZYV/action/replication_record"}},"created_at":"2026-07-05T08:06:04.675793+00:00","updated_at":"2026-07-05T08:06:04.675793+00:00"}