{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:USEANPOAX4KPWRQ7V2RV7JB54H","short_pith_number":"pith:USEANPOA","schema_version":"1.0","canonical_sha256":"a48806bdc0bf14fb461faea35fa43de1c406e4e5618b5ed19a0ee45f45344353","source":{"kind":"arxiv","id":"2204.05176","version":1},"attestation_state":"computed","paper":{"title":"Towards Painless Policy Optimization for Constrained MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arushi Jain, Csaba Szepesvari, Doina Precup, Reza Babanezhad, Sharan Vaswani","submitted_at":"2022-04-11T15:08:09Z","abstract_excerpt":"We study policy optimization in an infinite horizon, $\\gamma$-discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected reward with a small constraint violation. We consider the online setting with linear function approximation and assume global access to the corresponding features. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms in terms of their primal and dual regret on online linear optimization problems. We instantiate this framework "},"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":"2204.05176","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T15:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"227c00f4c18c3b88fb7e64d6c613e284aadaa8c6261356324f0f66eb040593cc","abstract_canon_sha256":"8c2c7aa8efc78133a9f60c179aa49807d9945dbc35f25fe6c2b87ec46ed9bebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:18.171023Z","signature_b64":"tnCqvwfTYlMh6HHCxT3nc9ObfYX9hiRCF1Z6c0x+UEz9H3Sz2MU2mfJhy3P4u9mtzxYObBBrCmsOBP1zqxL1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a48806bdc0bf14fb461faea35fa43de1c406e4e5618b5ed19a0ee45f45344353","last_reissued_at":"2026-07-05T04:13:18.170564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:18.170564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Painless Policy Optimization for Constrained MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arushi Jain, Csaba Szepesvari, Doina Precup, Reza Babanezhad, Sharan Vaswani","submitted_at":"2022-04-11T15:08:09Z","abstract_excerpt":"We study policy optimization in an infinite horizon, $\\gamma$-discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected reward with a small constraint violation. We consider the online setting with linear function approximation and assume global access to the corresponding features. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms in terms of their primal and dual regret on online linear optimization problems. We instantiate this framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05176","kind":"arxiv","version":1},"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/2204.05176/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":"2204.05176","created_at":"2026-07-05T04:13:18.170621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05176v1","created_at":"2026-07-05T04:13:18.170621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05176","created_at":"2026-07-05T04:13:18.170621+00:00"},{"alias_kind":"pith_short_12","alias_value":"USEANPOAX4KP","created_at":"2026-07-05T04:13:18.170621+00:00"},{"alias_kind":"pith_short_16","alias_value":"USEANPOAX4KPWRQ7","created_at":"2026-07-05T04:13:18.170621+00:00"},{"alias_kind":"pith_short_8","alias_value":"USEANPOA","created_at":"2026-07-05T04:13:18.170621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H","json":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H.json","graph_json":"https://pith.science/api/pith-number/USEANPOAX4KPWRQ7V2RV7JB54H/graph.json","events_json":"https://pith.science/api/pith-number/USEANPOAX4KPWRQ7V2RV7JB54H/events.json","paper":"https://pith.science/paper/USEANPOA"},"agent_actions":{"view_html":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H","download_json":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H.json","view_paper":"https://pith.science/paper/USEANPOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05176&json=true","fetch_graph":"https://pith.science/api/pith-number/USEANPOAX4KPWRQ7V2RV7JB54H/graph.json","fetch_events":"https://pith.science/api/pith-number/USEANPOAX4KPWRQ7V2RV7JB54H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/action/storage_attestation","attest_author":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/action/author_attestation","sign_citation":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/action/citation_signature","submit_replication":"https://pith.science/pith/USEANPOAX4KPWRQ7V2RV7JB54H/action/replication_record"}},"created_at":"2026-07-05T04:13:18.170621+00:00","updated_at":"2026-07-05T04:13:18.170621+00:00"}