{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GSHFY3LCOWJF4INGSR43ZSXWAL","short_pith_number":"pith:GSHFY3LC","schema_version":"1.0","canonical_sha256":"348e5c6d6275925e21a69479bccaf602db2da6512734bd4acfcbc4f4657db8b4","source":{"kind":"arxiv","id":"2312.12065","version":2},"attestation_state":"computed","paper":{"title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"I-Chen Wu, Kuo-Hao Ho, Nai-Chieh Huang, Ping-Chun Hsieh","submitted_at":"2023-12-19T11:33:18Z","abstract_excerpt":"Proximal Policy Optimization algorithm employing a clipped surrogate objective (PPO-Clip) is a prominent exemplar of the policy optimization methods. However, despite its remarkable empirical success, PPO-Clip lacks theoretical substantiation to date. In this paper, we contribute to the field by establishing the first global convergence results of a PPO-Clip variant in both tabular and neural function approximation settings. Our findings highlight the $O(1/\\sqrt{T})$ min-iterate convergence rate specifically in the context of neural function approximation. We tackle the inherent challenges in "},"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":"2312.12065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T11:33:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e0166455fe9bd14b020005b07fc5ddaa694eda70673194f961c2106c14fa951","abstract_canon_sha256":"63481111f784cfb509929de9c97a3f50ae5a3dd28aaf9f7447ea353700f52ec2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:28.997849Z","signature_b64":"CUZ8ZkbVSbNMtPvTz4/6SQIusG6nDUz9AfujTQTqJnJdXPyNyh3PKQiPaoAwFvH0/FIGST3KpWW5ZXBjrZxBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"348e5c6d6275925e21a69479bccaf602db2da6512734bd4acfcbc4f4657db8b4","last_reissued_at":"2026-07-05T07:46:28.997289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:28.997289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"I-Chen Wu, Kuo-Hao Ho, Nai-Chieh Huang, Ping-Chun Hsieh","submitted_at":"2023-12-19T11:33:18Z","abstract_excerpt":"Proximal Policy Optimization algorithm employing a clipped surrogate objective (PPO-Clip) is a prominent exemplar of the policy optimization methods. However, despite its remarkable empirical success, PPO-Clip lacks theoretical substantiation to date. In this paper, we contribute to the field by establishing the first global convergence results of a PPO-Clip variant in both tabular and neural function approximation settings. Our findings highlight the $O(1/\\sqrt{T})$ min-iterate convergence rate specifically in the context of neural function approximation. We tackle the inherent challenges in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12065","kind":"arxiv","version":2},"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/2312.12065/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":"2312.12065","created_at":"2026-07-05T07:46:28.997361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12065v2","created_at":"2026-07-05T07:46:28.997361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12065","created_at":"2026-07-05T07:46:28.997361+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSHFY3LCOWJF","created_at":"2026-07-05T07:46:28.997361+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSHFY3LCOWJF4ING","created_at":"2026-07-05T07:46:28.997361+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSHFY3LC","created_at":"2026-07-05T07:46:28.997361+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/GSHFY3LCOWJF4INGSR43ZSXWAL","json":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL.json","graph_json":"https://pith.science/api/pith-number/GSHFY3LCOWJF4INGSR43ZSXWAL/graph.json","events_json":"https://pith.science/api/pith-number/GSHFY3LCOWJF4INGSR43ZSXWAL/events.json","paper":"https://pith.science/paper/GSHFY3LC"},"agent_actions":{"view_html":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL","download_json":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL.json","view_paper":"https://pith.science/paper/GSHFY3LC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12065&json=true","fetch_graph":"https://pith.science/api/pith-number/GSHFY3LCOWJF4INGSR43ZSXWAL/graph.json","fetch_events":"https://pith.science/api/pith-number/GSHFY3LCOWJF4INGSR43ZSXWAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL/action/storage_attestation","attest_author":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL/action/author_attestation","sign_citation":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL/action/citation_signature","submit_replication":"https://pith.science/pith/GSHFY3LCOWJF4INGSR43ZSXWAL/action/replication_record"}},"created_at":"2026-07-05T07:46:28.997361+00:00","updated_at":"2026-07-05T07:46:28.997361+00:00"}