{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IWRLYYQTRZIWSM3WPXINZDSGE3","short_pith_number":"pith:IWRLYYQT","schema_version":"1.0","canonical_sha256":"45a2bc62138e516933767dd0dc8e4626ca3d3d21dc80e3853dbabd474e85fe86","source":{"kind":"arxiv","id":"2302.01450","version":3},"attestation_state":"computed","paper":{"title":"Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Mehrdad Moharrami, R. Srikant, Yashaswini Murthy","submitted_at":"2023-02-02T22:37:47Z","abstract_excerpt":"Many policy-based reinforcement learning (RL) algorithms can be viewed as instantiations of approximate policy iteration (PI), i.e., where policy improvement and policy evaluation are both performed approximately. In applications where the average reward objective is the meaningful performance metric, discounted reward formulations are often used with the discount factor being close to $1,$ which is equivalent to making the expected horizon very large. However, the corresponding theoretical bounds for error performance scale with the square of the horizon. Thus, even after dividing the total r"},"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":"2302.01450","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T22:37:47Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"06384661ce654903c9d5da222c584b713c96f227e0b7d0a6c1764ec1032e32f7","abstract_canon_sha256":"60e894c1dbe5c53758718bad6ac48bf088b03d6f29ce69dc6135c2225f5ea4f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:39.721611Z","signature_b64":"Qjop+UtU3PI1FxcnbTlWdWh7OlbphdIbQ3qx//9nj1hA3J+meeXql5qCkMrx6rax0uwNmAL2I/urlLT0IXAlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45a2bc62138e516933767dd0dc8e4626ca3d3d21dc80e3853dbabd474e85fe86","last_reissued_at":"2026-07-05T06:25:39.721115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:39.721115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Mehrdad Moharrami, R. Srikant, Yashaswini Murthy","submitted_at":"2023-02-02T22:37:47Z","abstract_excerpt":"Many policy-based reinforcement learning (RL) algorithms can be viewed as instantiations of approximate policy iteration (PI), i.e., where policy improvement and policy evaluation are both performed approximately. In applications where the average reward objective is the meaningful performance metric, discounted reward formulations are often used with the discount factor being close to $1,$ which is equivalent to making the expected horizon very large. However, the corresponding theoretical bounds for error performance scale with the square of the horizon. Thus, even after dividing the total r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01450","kind":"arxiv","version":3},"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/2302.01450/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":"2302.01450","created_at":"2026-07-05T06:25:39.721172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01450v3","created_at":"2026-07-05T06:25:39.721172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01450","created_at":"2026-07-05T06:25:39.721172+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWRLYYQTRZIW","created_at":"2026-07-05T06:25:39.721172+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWRLYYQTRZIWSM3W","created_at":"2026-07-05T06:25:39.721172+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWRLYYQT","created_at":"2026-07-05T06:25:39.721172+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/IWRLYYQTRZIWSM3WPXINZDSGE3","json":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3.json","graph_json":"https://pith.science/api/pith-number/IWRLYYQTRZIWSM3WPXINZDSGE3/graph.json","events_json":"https://pith.science/api/pith-number/IWRLYYQTRZIWSM3WPXINZDSGE3/events.json","paper":"https://pith.science/paper/IWRLYYQT"},"agent_actions":{"view_html":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3","download_json":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3.json","view_paper":"https://pith.science/paper/IWRLYYQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01450&json=true","fetch_graph":"https://pith.science/api/pith-number/IWRLYYQTRZIWSM3WPXINZDSGE3/graph.json","fetch_events":"https://pith.science/api/pith-number/IWRLYYQTRZIWSM3WPXINZDSGE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3/action/storage_attestation","attest_author":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3/action/author_attestation","sign_citation":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3/action/citation_signature","submit_replication":"https://pith.science/pith/IWRLYYQTRZIWSM3WPXINZDSGE3/action/replication_record"}},"created_at":"2026-07-05T06:25:39.721172+00:00","updated_at":"2026-07-05T06:25:39.721172+00:00"}