{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TEO3RAORIXLPQMQKTLG3J5MXVM","short_pith_number":"pith:TEO3RAOR","schema_version":"1.0","canonical_sha256":"991db881d145d6f8320a9acdb4f597ab3d7f7d52326acc5ba4c1f8f2c0f944a5","source":{"kind":"arxiv","id":"2205.10047","version":6},"attestation_state":"computed","paper":{"title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bei Jiang, Dongcui Diao, Haiyin Piao, Hechang Chen, Hengshuai Yao, Randy Goebel, Xing Chen, Yi Chang, Zhiwei Yang, Zhixiao Sun","submitted_at":"2022-05-20T09:38:04Z","abstract_excerpt":"The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is ``YES'', and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in ``off-policyness'', according to an off-policy metric called DEON. Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservati"},"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":"2205.10047","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T09:38:04Z","cross_cats_sorted":[],"title_canon_sha256":"6edfe6500706a31eb59fad519ee2282d14a8348671427ae325fc45dc2a28ba4d","abstract_canon_sha256":"432f9089b02cc500e462c615289f64913e82a05052b3ff838aff43ee4e976546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:53.771930Z","signature_b64":"cQrc2quYiE0lLFZW9NXLueggIHupUEyMaeAtky+RJDhdiWvqaZuxa29W6gGvW1TMP0L9zbmCxT4ZXXfABmWPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"991db881d145d6f8320a9acdb4f597ab3d7f7d52326acc5ba4c1f8f2c0f944a5","last_reissued_at":"2026-07-05T05:21:53.771519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:53.771519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bei Jiang, Dongcui Diao, Haiyin Piao, Hechang Chen, Hengshuai Yao, Randy Goebel, Xing Chen, Yi Chang, Zhiwei Yang, Zhixiao Sun","submitted_at":"2022-05-20T09:38:04Z","abstract_excerpt":"The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is ``YES'', and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in ``off-policyness'', according to an off-policy metric called DEON. Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10047","kind":"arxiv","version":6},"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/2205.10047/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":"2205.10047","created_at":"2026-07-05T05:21:53.771584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10047v6","created_at":"2026-07-05T05:21:53.771584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10047","created_at":"2026-07-05T05:21:53.771584+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEO3RAORIXLP","created_at":"2026-07-05T05:21:53.771584+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEO3RAORIXLPQMQK","created_at":"2026-07-05T05:21:53.771584+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEO3RAOR","created_at":"2026-07-05T05:21:53.771584+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/TEO3RAORIXLPQMQKTLG3J5MXVM","json":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM.json","graph_json":"https://pith.science/api/pith-number/TEO3RAORIXLPQMQKTLG3J5MXVM/graph.json","events_json":"https://pith.science/api/pith-number/TEO3RAORIXLPQMQKTLG3J5MXVM/events.json","paper":"https://pith.science/paper/TEO3RAOR"},"agent_actions":{"view_html":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM","download_json":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM.json","view_paper":"https://pith.science/paper/TEO3RAOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10047&json=true","fetch_graph":"https://pith.science/api/pith-number/TEO3RAORIXLPQMQKTLG3J5MXVM/graph.json","fetch_events":"https://pith.science/api/pith-number/TEO3RAORIXLPQMQKTLG3J5MXVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM/action/storage_attestation","attest_author":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM/action/author_attestation","sign_citation":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM/action/citation_signature","submit_replication":"https://pith.science/pith/TEO3RAORIXLPQMQKTLG3J5MXVM/action/replication_record"}},"created_at":"2026-07-05T05:21:53.771584+00:00","updated_at":"2026-07-05T05:21:53.771584+00:00"}