{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VSC5P2P7FGB2I3B3FLGLPOHQGU","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":"1923ead5c2962c724c2de2e0d92ec7febcc30c58b9b777c427299ac3241f7ff9","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-23T19:30:46Z","title_canon_sha256":"543da3edc3304b4af7ab4b84cc6615773582d1a9903c21718d2bcf7ab86be260"},"schema_version":"1.0","source":{"id":"2009.11348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.11348","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"arxiv_version","alias_value":"2009.11348v1","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.11348","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"pith_short_12","alias_value":"VSC5P2P7FGB2","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"pith_short_16","alias_value":"VSC5P2P7FGB2I3B3","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"pith_short_8","alias_value":"VSC5P2P7","created_at":"2026-07-05T01:37:44Z"}],"graph_snapshots":[{"event_id":"sha256:a7a4a0242b1854fbddfe2495ccb0d5d611b038d7ff93b294412b500ab26a60e5","target":"graph","created_at":"2026-07-05T01:37:44Z","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/2009.11348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Krishna C. Kalagarla, Pierluigi Nuzzo, Rahul Jain","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-23T19:30:46Z","title":"A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.11348","kind":"arxiv","version":1},"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":"sha256:6b09c0c9b621d5d1c15ddccfbf5372d1f770d53993f42caab421aa2a44196c71","target":"record","created_at":"2026-07-05T01:37:44Z","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":"1923ead5c2962c724c2de2e0d92ec7febcc30c58b9b777c427299ac3241f7ff9","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-23T19:30:46Z","title_canon_sha256":"543da3edc3304b4af7ab4b84cc6615773582d1a9903c21718d2bcf7ab86be260"},"schema_version":"1.0","source":{"id":"2009.11348","kind":"arxiv","version":1}},"canonical_sha256":"ac85d7e9ff2983a46c3b2accb7b8f0351d8c4f60608523096d48303dda75050e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac85d7e9ff2983a46c3b2accb7b8f0351d8c4f60608523096d48303dda75050e","first_computed_at":"2026-07-05T01:37:44.783019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:44.783019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z6V5CR7eHXqkGVVHZtmsSDqKFPOLLduarI41LA6JDO0ZePtrvjus6a4r8lF6AAFes6YqtNB/6M2EVhHCulX6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:44.783415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.11348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b09c0c9b621d5d1c15ddccfbf5372d1f770d53993f42caab421aa2a44196c71","sha256:a7a4a0242b1854fbddfe2495ccb0d5d611b038d7ff93b294412b500ab26a60e5"],"state_sha256":"4cb0be23cdcec5324e969bb2031b98d4c71bd7f817932ad39f1a15147de9687b"}