{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HSLGKSCRLGS665YXX443F5ZMAP","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":"ca78103b315eb0669a3d6eceaa4c3ce4aee884863628c58831a24437027c3083","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-23T17:54:31Z","title_canon_sha256":"742ceb40598b699dbed83877437200e2d39a357b8456585c13291c9339baebd3"},"schema_version":"1.0","source":{"id":"2206.11889","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.11889","created_at":"2026-07-05T05:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2206.11889v3","created_at":"2026-07-05T05:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11889","created_at":"2026-07-05T05:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"HSLGKSCRLGS6","created_at":"2026-07-05T05:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"HSLGKSCRLGS665YX","created_at":"2026-07-05T05:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"HSLGKSCR","created_at":"2026-07-05T05:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:ed64d5735d77c33a182a9ae4240acd3bcfcadc1cb976924ecfa11ae58dcc257e","target":"graph","created_at":"2026-07-05T05:31:15Z","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/2206.11889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the constrained reinforcement learning problem, in which an agent aims to maximize the expected cumulative reward subject to a constraint on the expected total value of a utility function. In contrast to existing model-based approaches or model-free methods accompanied with a `simulator', we aim to develop the first model-free, simulator-free algorithm that achieves a sublinear regret and a sublinear constraint violation even in large-scale systems. To this end, we consider the episodic constrained Markov decision processes with linear function approximation, where the transition dyna","authors_text":"Arnob Ghosh, Ness Shroff, Xingyu Zhou","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-23T17:54:31Z","title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11889","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:fd0c0e632904f4f2d4400c2c10f6d0ae1fff4a8de6f3b01f52aa08baaf813a7d","target":"record","created_at":"2026-07-05T05:31:15Z","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":"ca78103b315eb0669a3d6eceaa4c3ce4aee884863628c58831a24437027c3083","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-23T17:54:31Z","title_canon_sha256":"742ceb40598b699dbed83877437200e2d39a357b8456585c13291c9339baebd3"},"schema_version":"1.0","source":{"id":"2206.11889","kind":"arxiv","version":3}},"canonical_sha256":"3c9665485159a5ef7717bf39b2f72c03d763f09ed08f8c82a77e27291659e658","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c9665485159a5ef7717bf39b2f72c03d763f09ed08f8c82a77e27291659e658","first_computed_at":"2026-07-05T05:31:15.234030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:15.234030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"//rose0ob4IaCg+0Sw+XHCl8kcd4zGb+KX4wLqejtvlD2AvU5AqG9D0+w23hsk2B2+PSF0VfG9Xccdgvhm3WDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:15.234477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.11889","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd0c0e632904f4f2d4400c2c10f6d0ae1fff4a8de6f3b01f52aa08baaf813a7d","sha256:ed64d5735d77c33a182a9ae4240acd3bcfcadc1cb976924ecfa11ae58dcc257e"],"state_sha256":"a34f8cca14f25f2ddbbe0bcd20c6c5b3821bfb3be4feaff1b417eb303af0833b"}