{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TEO3RAORIXLPQMQKTLG3J5MXVM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"432f9089b02cc500e462c615289f64913e82a05052b3ff838aff43ee4e976546","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T09:38:04Z","title_canon_sha256":"6edfe6500706a31eb59fad519ee2282d14a8348671427ae325fc45dc2a28ba4d"},"schema_version":"1.0","source":{"id":"2205.10047","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10047","created_at":"2026-07-05T05:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10047v6","created_at":"2026-07-05T05:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10047","created_at":"2026-07-05T05:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"TEO3RAORIXLP","created_at":"2026-07-05T05:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"TEO3RAORIXLPQMQK","created_at":"2026-07-05T05:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"TEO3RAOR","created_at":"2026-07-05T05:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:f79236b274599fd3d3cf32ceab106711b16db3e2bd50a56b7ac1ac32fc0add0b","target":"graph","created_at":"2026-07-05T05:21:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.10047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bei Jiang, Dongcui Diao, Haiyin Piao, Hechang Chen, Hengshuai Yao, Randy Goebel, Xing Chen, Yi Chang, Zhiwei Yang, Zhixiao Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T09:38:04Z","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10047","kind":"arxiv","version":6},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5d7aae3c57e4cfda30f1d2f80932439a3fc544d17853fd45fb3516d52e15f1b5","target":"record","created_at":"2026-07-05T05:21:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"432f9089b02cc500e462c615289f64913e82a05052b3ff838aff43ee4e976546","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T09:38:04Z","title_canon_sha256":"6edfe6500706a31eb59fad519ee2282d14a8348671427ae325fc45dc2a28ba4d"},"schema_version":"1.0","source":{"id":"2205.10047","kind":"arxiv","version":6}},"canonical_sha256":"991db881d145d6f8320a9acdb4f597ab3d7f7d52326acc5ba4c1f8f2c0f944a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"991db881d145d6f8320a9acdb4f597ab3d7f7d52326acc5ba4c1f8f2c0f944a5","first_computed_at":"2026-07-05T05:21:53.771519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:53.771519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cQrc2quYiE0lLFZW9NXLueggIHupUEyMaeAtky+RJDhdiWvqaZuxa29W6gGvW1TMP0L9zbmCxT4ZXXfABmWPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:53.771930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10047","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d7aae3c57e4cfda30f1d2f80932439a3fc544d17853fd45fb3516d52e15f1b5","sha256:f79236b274599fd3d3cf32ceab106711b16db3e2bd50a56b7ac1ac32fc0add0b"],"state_sha256":"4bcaaff15853b3047602ea14107cca4c08c5636ae78fd8d9049b334f25da0abc"}