{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FIBCI6LT5JRXA3F7W42UZBHZYV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ca9eeea99c4f5dbb171de0a6c2d78f97e19704201716a5ae9f44636d16028904","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-09T09:03:06Z","title_canon_sha256":"a58294986390d57428fae09d70f1716762dfbd9519e7307c564e4fff8736b3eb"},"schema_version":"1.0","source":{"id":"2404.06136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06136","created_at":"2026-07-05T08:06:04Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06136v1","created_at":"2026-07-05T08:06:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06136","created_at":"2026-07-05T08:06:04Z"},{"alias_kind":"pith_short_12","alias_value":"FIBCI6LT5JRX","created_at":"2026-07-05T08:06:04Z"},{"alias_kind":"pith_short_16","alias_value":"FIBCI6LT5JRXA3F7","created_at":"2026-07-05T08:06:04Z"},{"alias_kind":"pith_short_8","alias_value":"FIBCI6LT","created_at":"2026-07-05T08:06:04Z"}],"graph_snapshots":[{"event_id":"sha256:cf5781a001d8434187a01a79fa51522ab5935f8cabf87d96345c54829adde513","target":"graph","created_at":"2026-07-05T08:06:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.06136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dominic Liao-McPherson, Efe Balta, John Lygeros, Matilde Gargiani, Robin Sieber","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-09T09:03:06Z","title":"Inexact Policy Iteration Methods for Large-Scale Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06136","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80c902b227b842f062d3ea94a64717f25ef38e0531a51ce27044b6cf55239544","target":"record","created_at":"2026-07-05T08:06:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ca9eeea99c4f5dbb171de0a6c2d78f97e19704201716a5ae9f44636d16028904","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-09T09:03:06Z","title_canon_sha256":"a58294986390d57428fae09d70f1716762dfbd9519e7307c564e4fff8736b3eb"},"schema_version":"1.0","source":{"id":"2404.06136","kind":"arxiv","version":1}},"canonical_sha256":"2a02247973ea63706cbfb7354c84f9c5478ec9df01cfb14d1e794aaf1ac96085","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a02247973ea63706cbfb7354c84f9c5478ec9df01cfb14d1e794aaf1ac96085","first_computed_at":"2026-07-05T08:06:04.675728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:04.675728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HCpr5QEMqGHMuTdvS1dVxTsMIeIsrvX8E/1v1ZWGHtK7wvpDGv4F4KptbiVdvJ+Nqylh6ULCrT109y4ohnWFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:04.676238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80c902b227b842f062d3ea94a64717f25ef38e0531a51ce27044b6cf55239544","sha256:cf5781a001d8434187a01a79fa51522ab5935f8cabf87d96345c54829adde513"],"state_sha256":"87e7172cc50405774b540f5a7d3e09eb8d62ac7b4fa3f69e4a888d49f2da45b6"}