{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4YLGKXFHLWBHKMPFIHSEXQCDO2","short_pith_number":"pith:4YLGKXFH","schema_version":"1.0","canonical_sha256":"e616655ca75d827531e541e44bc0437683f5fcef313bd694c5f5123245650cc0","source":{"kind":"arxiv","id":"2406.03894","version":1},"attestation_state":"computed","paper":{"title":"Transductive Off-policy Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junliang Xing, Renye Yan, Xiaoyang Tan, Yaozhong Gan, Zhe Wu","submitted_at":"2024-06-06T09:29:40Z","abstract_excerpt":"Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies is constrained. This paper introduces a novel off-policy extension to the original PPO method, christened Transductive Off-policy PPO (ToPPO). Herein, we provide theoretical justification for incorporating off-policy data in PPO training and prudent guidelines for its safe application. Our contribution includes a novel formulation of the policy improvement "},"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":"2406.03894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T09:29:40Z","cross_cats_sorted":[],"title_canon_sha256":"2bcdf8470815c81c5eddda5dc836ef0c498b70c4bf86c0697187aaff74c7299a","abstract_canon_sha256":"44996ec8aac1a43c243b53aa486b625656d453401625fa70c9ff999e43e506d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:17.550073Z","signature_b64":"91gSrNvEMY5a3aA2J9DdbiZwRDLXvDkeXyk98qMoxbzZR2x8ffHXNFEC63vk5Bws4Mdj1fw0a/hrfqdbRsdRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e616655ca75d827531e541e44bc0437683f5fcef313bd694c5f5123245650cc0","last_reissued_at":"2026-07-05T08:28:17.549611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:17.549611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transductive Off-policy Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junliang Xing, Renye Yan, Xiaoyang Tan, Yaozhong Gan, Zhe Wu","submitted_at":"2024-06-06T09:29:40Z","abstract_excerpt":"Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies is constrained. This paper introduces a novel off-policy extension to the original PPO method, christened Transductive Off-policy PPO (ToPPO). Herein, we provide theoretical justification for incorporating off-policy data in PPO training and prudent guidelines for its safe application. Our contribution includes a novel formulation of the policy improvement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03894","kind":"arxiv","version":1},"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/2406.03894/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":"2406.03894","created_at":"2026-07-05T08:28:17.549668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03894v1","created_at":"2026-07-05T08:28:17.549668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03894","created_at":"2026-07-05T08:28:17.549668+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YLGKXFHLWBH","created_at":"2026-07-05T08:28:17.549668+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YLGKXFHLWBHKMPF","created_at":"2026-07-05T08:28:17.549668+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YLGKXFH","created_at":"2026-07-05T08:28:17.549668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03382","citing_title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2509.09838","citing_title":"Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2","json":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2.json","graph_json":"https://pith.science/api/pith-number/4YLGKXFHLWBHKMPFIHSEXQCDO2/graph.json","events_json":"https://pith.science/api/pith-number/4YLGKXFHLWBHKMPFIHSEXQCDO2/events.json","paper":"https://pith.science/paper/4YLGKXFH"},"agent_actions":{"view_html":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2","download_json":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2.json","view_paper":"https://pith.science/paper/4YLGKXFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03894&json=true","fetch_graph":"https://pith.science/api/pith-number/4YLGKXFHLWBHKMPFIHSEXQCDO2/graph.json","fetch_events":"https://pith.science/api/pith-number/4YLGKXFHLWBHKMPFIHSEXQCDO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2/action/storage_attestation","attest_author":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2/action/author_attestation","sign_citation":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2/action/citation_signature","submit_replication":"https://pith.science/pith/4YLGKXFHLWBHKMPFIHSEXQCDO2/action/replication_record"}},"created_at":"2026-07-05T08:28:17.549668+00:00","updated_at":"2026-07-05T08:28:17.549668+00:00"}