{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:N4ZRSSZOGOYU3DVXE26GHZIIMH","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":"8bcc1804ecd8774679f19de7872664120427c27c15f61cca2d427408f89180c1","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-28T19:45:16Z","title_canon_sha256":"25aab5251eff283f52aad37ff3a7a3a3fd0df63be8f47f1161fa205026ad1771"},"schema_version":"1.0","source":{"id":"1911.12842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.12842","created_at":"2026-07-05T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1911.12842v1","created_at":"2026-07-05T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12842","created_at":"2026-07-05T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"N4ZRSSZOGOYU","created_at":"2026-07-05T00:22:49Z"},{"alias_kind":"pith_short_16","alias_value":"N4ZRSSZOGOYU3DVX","created_at":"2026-07-05T00:22:49Z"},{"alias_kind":"pith_short_8","alias_value":"N4ZRSSZO","created_at":"2026-07-05T00:22:49Z"}],"graph_snapshots":[{"event_id":"sha256:39b7105f822b4907a59d58a21c477c4c77056a879a9eb9577bbb7092007eee24","target":"graph","created_at":"2026-07-05T00:22:49Z","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/1911.12842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy iteration is a family of algorithms that are used to find an optimal policy for a given Markov Decision Problem (MDP). Simple Policy iteration (SPI) is a type of policy iteration where the strategy is to change the policy at exactly one improvable state at every step. Melekopoglou and Condon [1990] showed an exponential lower bound on the number of iterations taken by SPI for a 2 action MDP. The results have not been generalized to $k-$action MDP since. In this paper, we revisit the algorithm and the analysis done by Melekopoglou and Condon. We generalize the previous result and prove a","authors_text":"Bhishma Dedhia, Kumar Ashutosh, Parthasarathi Khirwadkar, Sarthak Consul","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-28T19:45:16Z","title":"Analysis of Lower Bounds for Simple Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12842","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:e17d8a06eb2b7ef1fe4c5b86ac50de53e019b88c5faf59cd1d2d25fbe0f49526","target":"record","created_at":"2026-07-05T00:22:49Z","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":"8bcc1804ecd8774679f19de7872664120427c27c15f61cca2d427408f89180c1","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-28T19:45:16Z","title_canon_sha256":"25aab5251eff283f52aad37ff3a7a3a3fd0df63be8f47f1161fa205026ad1771"},"schema_version":"1.0","source":{"id":"1911.12842","kind":"arxiv","version":1}},"canonical_sha256":"6f33194b2e33b14d8eb726bc63e50861cdeef37ec705e0280b4023cd210d0ec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f33194b2e33b14d8eb726bc63e50861cdeef37ec705e0280b4023cd210d0ec5","first_computed_at":"2026-07-05T00:22:49.529763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:22:49.529763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Be0/h8GOwfqqEpxviC61TUU/1TZ/Y309wvPL3koFNmtMyG8Wb9Y7m4+oFcLXfkJoFt8WSUNHcQMInf+JOuneAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:22:49.530164Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.12842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e17d8a06eb2b7ef1fe4c5b86ac50de53e019b88c5faf59cd1d2d25fbe0f49526","sha256:39b7105f822b4907a59d58a21c477c4c77056a879a9eb9577bbb7092007eee24"],"state_sha256":"38404a3667848e658079d1a517194f46ccf9598eccebf0afce43220d25b16c4f"}