{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y3OLEY7VRYUUFXCUMMOQTTLLWO","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":"800d02873d90e1a133adf59e83e8f1c0eb60c4dfff3d83d5a254ae3a2409bf8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T14:31:52Z","title_canon_sha256":"5972644911079a050239581cfe733b49656b6a9b67ee02484b758e772ff4b60f"},"schema_version":"1.0","source":{"id":"2405.01327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01327","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01327v2","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01327","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"Y3OLEY7VRYUU","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"Y3OLEY7VRYUUFXCU","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"Y3OLEY7V","created_at":"2026-07-05T08:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:940394d76607bdb58207284466e8b6df7cd16e2f8d2ab1988c59939de1e7462b","target":"graph","created_at":"2026-07-05T08:14:57Z","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/2405.01327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied during training because there might be model mismatch between the training and real environments. To address the above challenge, we formulate the problem as constrained RL under model uncertainty, where the goal is to learn a good policy that optimizes the reward and at the same time satisfy the constraint under model mismatch. We develop a Robust Constrained P","authors_text":"Fei Miao, Shaofeng Zou, Sihong He, Zhongchang Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T14:31:52Z","title":"Constrained Reinforcement Learning Under Model Mismatch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01327","kind":"arxiv","version":2},"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":"sha256:66e1e59a402978a3b77fb5fe27609fc02ae1693305c1a9365af4c81d95ef9f46","target":"record","created_at":"2026-07-05T08:14:57Z","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":"800d02873d90e1a133adf59e83e8f1c0eb60c4dfff3d83d5a254ae3a2409bf8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T14:31:52Z","title_canon_sha256":"5972644911079a050239581cfe733b49656b6a9b67ee02484b758e772ff4b60f"},"schema_version":"1.0","source":{"id":"2405.01327","kind":"arxiv","version":2}},"canonical_sha256":"c6dcb263f58e2942dc54631d09cd6bb38b9cd2ef7fe0272cbc615edb18ac3454","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6dcb263f58e2942dc54631d09cd6bb38b9cd2ef7fe0272cbc615edb18ac3454","first_computed_at":"2026-07-05T08:14:57.288294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:57.288294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4aTj8fu/QFQjzRnnLw0sOA8G/T9ZWiXTlJgPzvKtmD+rj/lDpJba7Oj4UTWpawdbY4SO11lYVot+cyx8d+vADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:57.288771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66e1e59a402978a3b77fb5fe27609fc02ae1693305c1a9365af4c81d95ef9f46","sha256:940394d76607bdb58207284466e8b6df7cd16e2f8d2ab1988c59939de1e7462b"],"state_sha256":"2ad8021712dac4e2cd76fe750bf8b644433f5db452266542635673283835ec87"}