{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VSC5P2P7FGB2I3B3FLGLPOHQGU","short_pith_number":"pith:VSC5P2P7","schema_version":"1.0","canonical_sha256":"ac85d7e9ff2983a46c3b2accb7b8f0351d8c4f60608523096d48303dda75050e","source":{"kind":"arxiv","id":"2009.11348","version":1},"attestation_state":"computed","paper":{"title":"A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Krishna C. Kalagarla, Pierluigi Nuzzo, Rahul Jain","submitted_at":"2020-09-23T19:30:46Z","abstract_excerpt":"Constrained Markov Decision Processes (CMDPs) formalize sequential decision-making problems whose objective is to minimize a cost function while satisfying constraints on various cost functions. In this paper, we consider the setting of episodic fixed-horizon CMDPs. We propose an online algorithm which leverages the linear programming formulation of finite-horizon CMDP for repeated optimistic planning to provide a probably approximately correct (PAC) guarantee on the number of episodes needed to ensure an $\\epsilon$-optimal policy, i.e., with resulting objective value within $\\epsilon$ of the "},"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":"2009.11348","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-23T19:30:46Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"543da3edc3304b4af7ab4b84cc6615773582d1a9903c21718d2bcf7ab86be260","abstract_canon_sha256":"1923ead5c2962c724c2de2e0d92ec7febcc30c58b9b777c427299ac3241f7ff9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:44.783415Z","signature_b64":"Z6V5CR7eHXqkGVVHZtmsSDqKFPOLLduarI41LA6JDO0ZePtrvjus6a4r8lF6AAFes6YqtNB/6M2EVhHCulX6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac85d7e9ff2983a46c3b2accb7b8f0351d8c4f60608523096d48303dda75050e","last_reissued_at":"2026-07-05T01:37:44.783019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:44.783019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Krishna C. Kalagarla, Pierluigi Nuzzo, Rahul Jain","submitted_at":"2020-09-23T19:30:46Z","abstract_excerpt":"Constrained Markov Decision Processes (CMDPs) formalize sequential decision-making problems whose objective is to minimize a cost function while satisfying constraints on various cost functions. In this paper, we consider the setting of episodic fixed-horizon CMDPs. We propose an online algorithm which leverages the linear programming formulation of finite-horizon CMDP for repeated optimistic planning to provide a probably approximately correct (PAC) guarantee on the number of episodes needed to ensure an $\\epsilon$-optimal policy, i.e., with resulting objective value within $\\epsilon$ of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.11348","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/2009.11348/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":"2009.11348","created_at":"2026-07-05T01:37:44.783081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.11348v1","created_at":"2026-07-05T01:37:44.783081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.11348","created_at":"2026-07-05T01:37:44.783081+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSC5P2P7FGB2","created_at":"2026-07-05T01:37:44.783081+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSC5P2P7FGB2I3B3","created_at":"2026-07-05T01:37:44.783081+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSC5P2P7","created_at":"2026-07-05T01:37:44.783081+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/VSC5P2P7FGB2I3B3FLGLPOHQGU","json":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU.json","graph_json":"https://pith.science/api/pith-number/VSC5P2P7FGB2I3B3FLGLPOHQGU/graph.json","events_json":"https://pith.science/api/pith-number/VSC5P2P7FGB2I3B3FLGLPOHQGU/events.json","paper":"https://pith.science/paper/VSC5P2P7"},"agent_actions":{"view_html":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU","download_json":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU.json","view_paper":"https://pith.science/paper/VSC5P2P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.11348&json=true","fetch_graph":"https://pith.science/api/pith-number/VSC5P2P7FGB2I3B3FLGLPOHQGU/graph.json","fetch_events":"https://pith.science/api/pith-number/VSC5P2P7FGB2I3B3FLGLPOHQGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU/action/storage_attestation","attest_author":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU/action/author_attestation","sign_citation":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU/action/citation_signature","submit_replication":"https://pith.science/pith/VSC5P2P7FGB2I3B3FLGLPOHQGU/action/replication_record"}},"created_at":"2026-07-05T01:37:44.783081+00:00","updated_at":"2026-07-05T01:37:44.783081+00:00"}