{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6D7RG46CQ6VRRP6FUEDAEOUO2L","short_pith_number":"pith:6D7RG46C","schema_version":"1.0","canonical_sha256":"f0ff1373c287ab18bfc5a106023a8ed2e4f69fe286b78b15825569b102889be9","source":{"kind":"arxiv","id":"2401.16025","version":9},"attestation_state":"computed","paper":{"title":"Simple Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan Yang, Marco Hutter, Qiang Zhang, Renjing Xu, Zhengpeng Xie","submitted_at":"2024-01-29T10:17:54Z","abstract_excerpt":"Model-free reinforcement learning algorithms have seen remarkable progress, but key challenges remain. Trust Region Policy Optimization (TRPO) is known for ensuring monotonic policy improvement through conservative updates within a trust region, backed by strong theoretical guarantees. However, its reliance on complex second-order optimization limits its practical efficiency. Proximal Policy Optimization (PPO) addresses this by simplifying TRPO's approach using ratio clipping, improving efficiency but sacrificing some theoretical robustness. This raises a natural question: Can we combine the s"},"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":"2401.16025","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T10:17:54Z","cross_cats_sorted":[],"title_canon_sha256":"dbaa649a9567a809b7d8998c57dd5c8ab6100010972577e450b0b482f072af40","abstract_canon_sha256":"b3afd4ea3409e8e86bdfd9e500903077a57d95b5bc1f4b0454cd7596eb980358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:27.325644Z","signature_b64":"FcIt0rQzjKFVmy2bLtvAftvvP0nz75vDUgbAQK+aa84+x0wr1bavzU9pM+xdRu2wuuxPYjG6Kd3ul5GLziXaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ff1373c287ab18bfc5a106023a8ed2e4f69fe286b78b15825569b102889be9","last_reissued_at":"2026-07-05T11:43:27.324968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:27.324968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan Yang, Marco Hutter, Qiang Zhang, Renjing Xu, Zhengpeng Xie","submitted_at":"2024-01-29T10:17:54Z","abstract_excerpt":"Model-free reinforcement learning algorithms have seen remarkable progress, but key challenges remain. Trust Region Policy Optimization (TRPO) is known for ensuring monotonic policy improvement through conservative updates within a trust region, backed by strong theoretical guarantees. However, its reliance on complex second-order optimization limits its practical efficiency. Proximal Policy Optimization (PPO) addresses this by simplifying TRPO's approach using ratio clipping, improving efficiency but sacrificing some theoretical robustness. This raises a natural question: Can we combine the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16025","kind":"arxiv","version":9},"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/2401.16025/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":"2401.16025","created_at":"2026-07-05T11:43:27.325052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16025v9","created_at":"2026-07-05T11:43:27.325052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16025","created_at":"2026-07-05T11:43:27.325052+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D7RG46CQ6VR","created_at":"2026-07-05T11:43:27.325052+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D7RG46CQ6VRRP6F","created_at":"2026-07-05T11:43:27.325052+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D7RG46C","created_at":"2026-07-05T11:43:27.325052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09821","citing_title":"Rethinking the Divergence Regularization in LLM RL","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03382","citing_title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26784","citing_title":"Ratio-Variance Regularized Policy Optimization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18578","citing_title":"Bounded Ratio Reinforcement Learning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03065","citing_title":"OGPO: Sample Efficient Full-Finetuning of Generative Control Policies","ref_index":128,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L","json":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L.json","graph_json":"https://pith.science/api/pith-number/6D7RG46CQ6VRRP6FUEDAEOUO2L/graph.json","events_json":"https://pith.science/api/pith-number/6D7RG46CQ6VRRP6FUEDAEOUO2L/events.json","paper":"https://pith.science/paper/6D7RG46C"},"agent_actions":{"view_html":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L","download_json":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L.json","view_paper":"https://pith.science/paper/6D7RG46C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16025&json=true","fetch_graph":"https://pith.science/api/pith-number/6D7RG46CQ6VRRP6FUEDAEOUO2L/graph.json","fetch_events":"https://pith.science/api/pith-number/6D7RG46CQ6VRRP6FUEDAEOUO2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/action/storage_attestation","attest_author":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/action/author_attestation","sign_citation":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/action/citation_signature","submit_replication":"https://pith.science/pith/6D7RG46CQ6VRRP6FUEDAEOUO2L/action/replication_record"}},"created_at":"2026-07-05T11:43:27.325052+00:00","updated_at":"2026-07-05T11:43:27.325052+00:00"}