{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HSLGKSCRLGS665YXX443F5ZMAP","short_pith_number":"pith:HSLGKSCR","schema_version":"1.0","canonical_sha256":"3c9665485159a5ef7717bf39b2f72c03d763f09ed08f8c82a77e27291659e658","source":{"kind":"arxiv","id":"2206.11889","version":3},"attestation_state":"computed","paper":{"title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnob Ghosh, Ness Shroff, Xingyu Zhou","submitted_at":"2022-06-23T17:54:31Z","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"},"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":"2206.11889","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-23T17:54:31Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"742ceb40598b699dbed83877437200e2d39a357b8456585c13291c9339baebd3","abstract_canon_sha256":"ca78103b315eb0669a3d6eceaa4c3ce4aee884863628c58831a24437027c3083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:15.234477Z","signature_b64":"//rose0ob4IaCg+0Sw+XHCl8kcd4zGb+KX4wLqejtvlD2AvU5AqG9D0+w23hsk2B2+PSF0VfG9Xccdgvhm3WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c9665485159a5ef7717bf39b2f72c03d763f09ed08f8c82a77e27291659e658","last_reissued_at":"2026-07-05T05:31:15.234030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:15.234030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnob Ghosh, Ness Shroff, Xingyu Zhou","submitted_at":"2022-06-23T17:54:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11889","kind":"arxiv","version":3},"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/2206.11889/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":"2206.11889","created_at":"2026-07-05T05:31:15.234088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.11889v3","created_at":"2026-07-05T05:31:15.234088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11889","created_at":"2026-07-05T05:31:15.234088+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSLGKSCRLGS6","created_at":"2026-07-05T05:31:15.234088+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSLGKSCRLGS665YX","created_at":"2026-07-05T05:31:15.234088+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSLGKSCR","created_at":"2026-07-05T05:31:15.234088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05441","citing_title":"Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP","json":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP.json","graph_json":"https://pith.science/api/pith-number/HSLGKSCRLGS665YXX443F5ZMAP/graph.json","events_json":"https://pith.science/api/pith-number/HSLGKSCRLGS665YXX443F5ZMAP/events.json","paper":"https://pith.science/paper/HSLGKSCR"},"agent_actions":{"view_html":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP","download_json":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP.json","view_paper":"https://pith.science/paper/HSLGKSCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.11889&json=true","fetch_graph":"https://pith.science/api/pith-number/HSLGKSCRLGS665YXX443F5ZMAP/graph.json","fetch_events":"https://pith.science/api/pith-number/HSLGKSCRLGS665YXX443F5ZMAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP/action/storage_attestation","attest_author":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP/action/author_attestation","sign_citation":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP/action/citation_signature","submit_replication":"https://pith.science/pith/HSLGKSCRLGS665YXX443F5ZMAP/action/replication_record"}},"created_at":"2026-07-05T05:31:15.234088+00:00","updated_at":"2026-07-05T05:31:15.234088+00:00"}