{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IBK22QQUL5OZ7RCAKKHJP7DFOE","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":"544173e5385476ce4d6e6207092fb2bcd5c68fbc52f7db6a1d01386eb7ea1a3c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T16:05:14Z","title_canon_sha256":"1b46dc824d0da08e63ba056b027d713881d6d9379a879f16231bf89644a95c84"},"schema_version":"1.0","source":{"id":"2011.05869","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05869","created_at":"2026-07-05T02:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05869v3","created_at":"2026-07-05T02:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05869","created_at":"2026-07-05T02:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"IBK22QQUL5OZ","created_at":"2026-07-05T02:44:34Z"},{"alias_kind":"pith_short_16","alias_value":"IBK22QQUL5OZ7RCA","created_at":"2026-07-05T02:44:34Z"},{"alias_kind":"pith_short_8","alias_value":"IBK22QQU","created_at":"2026-07-05T02:44:34Z"}],"graph_snapshots":[{"event_id":"sha256:9c40a037984487f1529a386edfe3aaa6e0410fb35f209c57eb49555f6a2f9917","target":"graph","created_at":"2026-07-05T02:44:34Z","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/2011.05869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a number of expected total costs. In general, such SRL problems have nonconvex objective functions subject to multiple nonconvex constraints, and hence are very challenging to solve, particularly to provide a globally optimal policy. Many popular SRL algorithms adopt a primal-dual structure which utilizes the updating of dual variables for satisfying the constraints. In contrast, we propose a primal approach, called const","authors_text":"Guanghui Lan, Tengyu Xu, Yingbin Liang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T16:05:14Z","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05869","kind":"arxiv","version":3},"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":"sha256:855ada0933ac79440d2a71fe6400ff58e55a4137e0f13ac26f54521c4b5869ce","target":"record","created_at":"2026-07-05T02:44:34Z","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":"544173e5385476ce4d6e6207092fb2bcd5c68fbc52f7db6a1d01386eb7ea1a3c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T16:05:14Z","title_canon_sha256":"1b46dc824d0da08e63ba056b027d713881d6d9379a879f16231bf89644a95c84"},"schema_version":"1.0","source":{"id":"2011.05869","kind":"arxiv","version":3}},"canonical_sha256":"4055ad42145f5d9fc440528e97fc65712a6d80ca6c43107d40eddbd5bafa66f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4055ad42145f5d9fc440528e97fc65712a6d80ca6c43107d40eddbd5bafa66f7","first_computed_at":"2026-07-05T02:44:34.467390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:34.467390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sd9FsrlHmQDb9fZ6SUPni6nfrP2Gl4kVdsL/nc/8/Qo/JE41OFfhhxRrniS427pI6EkN7GePyPBr/2lAWHUaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:34.467879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.05869","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:855ada0933ac79440d2a71fe6400ff58e55a4137e0f13ac26f54521c4b5869ce","sha256:9c40a037984487f1529a386edfe3aaa6e0410fb35f209c57eb49555f6a2f9917"],"state_sha256":"119535d0cd6fa90aae1e5978fcca4ea4f6e681a0c87e4962a80c4de395bc21fd"}