{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:UCXOEZNIAVJ2DPZUABBXJDQXX2","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":"d8f41d317f511994238957d8214a31e73efb5cbc15c6e41e95baec41b1fc28d6","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-12T19:11:03Z","title_canon_sha256":"c6a0fe0edee0b837bd43c13056502de2e113cdc1f7bd78fefa5a26e24122c952"},"schema_version":"1.0","source":{"id":"1405.2878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.2878","created_at":"2026-05-18T02:52:04Z"},{"alias_kind":"arxiv_version","alias_value":"1405.2878v1","created_at":"2026-05-18T02:52:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.2878","created_at":"2026-05-18T02:52:04Z"},{"alias_kind":"pith_short_12","alias_value":"UCXOEZNIAVJ2","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"UCXOEZNIAVJ2DPZU","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"UCXOEZNI","created_at":"2026-05-18T12:28:52Z"}],"graph_snapshots":[{"event_id":"sha256:5b82e9f9cddacd5d10a40bc16cfe3b59aa75e32194f4bd895c189706dbc0bc1a","target":"graph","created_at":"2026-05-18T02:52:04Z","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"},"paper":{"abstract_excerpt":"We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on several approximate variations of the Policy Iteration algorithm: Approximate Policy Iteration, Conservative Policy Iteration (CPI), a natural adaptation of the Policy Search by Dynamic Programming algorithm to the infinite-horizon case (PSDP$_\\infty$), and the recently proposed Non-Stationary Policy iteration (NSPI(m)). For all algorithms, we describe performance bounds, and make a comparison by paying a particular attention to the concentrability constants involved, the nu","authors_text":"Bruno Scherrer (INRIA Nancy - Grand Est / LORIA)","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-12T19:11:03Z","title":"Approximate Policy Iteration Schemes: A Comparison"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.2878","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:ffef8d7ff31f88530d8d803fabf4d5ed4b92ba1eccec3537887801d9788f24e9","target":"record","created_at":"2026-05-18T02:52:04Z","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":"d8f41d317f511994238957d8214a31e73efb5cbc15c6e41e95baec41b1fc28d6","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-12T19:11:03Z","title_canon_sha256":"c6a0fe0edee0b837bd43c13056502de2e113cdc1f7bd78fefa5a26e24122c952"},"schema_version":"1.0","source":{"id":"1405.2878","kind":"arxiv","version":1}},"canonical_sha256":"a0aee265a80553a1bf340043748e17be9bd50d137a46e45cd32967df96b158ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0aee265a80553a1bf340043748e17be9bd50d137a46e45cd32967df96b158ac","first_computed_at":"2026-05-18T02:52:04.614481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:52:04.614481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+6o/V//iEyatc+L69EkZrf/HI04mjyTn3J33EihPHtS6Aa6NXnZWINHgdcmyMqU0Wk0aCkpq0WnfII0YAmu+CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:52:04.614904Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.2878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffef8d7ff31f88530d8d803fabf4d5ed4b92ba1eccec3537887801d9788f24e9","sha256:5b82e9f9cddacd5d10a40bc16cfe3b59aa75e32194f4bd895c189706dbc0bc1a"],"state_sha256":"01ae64103ae1cc61d77cd65a76aba73e5fe273847f51b9652c2b1c9a9d42cd1d"}