{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SSOLOD57GWJY3DW2FDB42UZM7D","short_pith_number":"pith:SSOLOD57","schema_version":"1.0","canonical_sha256":"949cb70fbf35938d8eda28c3cd532cf8d3f67002d9a8c4929f015dac1bc80bae","source":{"kind":"arxiv","id":"2105.13919","version":1},"attestation_state":"computed","paper":{"title":"Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Rahul Singh","submitted_at":"2021-05-28T15:36:01Z","abstract_excerpt":"We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE."},"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":"2105.13919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-05-28T15:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"205cd03febab8089cd77a5891df1aebf2a702b0c5487f080215d3130fd15eaca","abstract_canon_sha256":"55d1282cacf84162d7cf35d625397c703d299bf01e92306168a5e35fca57f9c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:12.581875Z","signature_b64":"9+dceOSbW8jaBmEVJtKPEISFylgaoZ2CzUHZym7DIv72vABIGHwSkimu/2st2bEcUPCmcnGVJBcVYz/dnoj5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"949cb70fbf35938d8eda28c3cd532cf8d3f67002d9a8c4929f015dac1bc80bae","last_reissued_at":"2026-07-05T02:44:12.581487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:12.581487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Rahul Singh","submitted_at":"2021-05-28T15:36:01Z","abstract_excerpt":"We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13919","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/2105.13919/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":"2105.13919","created_at":"2026-07-05T02:44:12.581553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13919v1","created_at":"2026-07-05T02:44:12.581553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13919","created_at":"2026-07-05T02:44:12.581553+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSOLOD57GWJY","created_at":"2026-07-05T02:44:12.581553+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSOLOD57GWJY3DW2","created_at":"2026-07-05T02:44:12.581553+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSOLOD57","created_at":"2026-07-05T02:44:12.581553+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/SSOLOD57GWJY3DW2FDB42UZM7D","json":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D.json","graph_json":"https://pith.science/api/pith-number/SSOLOD57GWJY3DW2FDB42UZM7D/graph.json","events_json":"https://pith.science/api/pith-number/SSOLOD57GWJY3DW2FDB42UZM7D/events.json","paper":"https://pith.science/paper/SSOLOD57"},"agent_actions":{"view_html":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D","download_json":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D.json","view_paper":"https://pith.science/paper/SSOLOD57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13919&json=true","fetch_graph":"https://pith.science/api/pith-number/SSOLOD57GWJY3DW2FDB42UZM7D/graph.json","fetch_events":"https://pith.science/api/pith-number/SSOLOD57GWJY3DW2FDB42UZM7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D/action/storage_attestation","attest_author":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D/action/author_attestation","sign_citation":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D/action/citation_signature","submit_replication":"https://pith.science/pith/SSOLOD57GWJY3DW2FDB42UZM7D/action/replication_record"}},"created_at":"2026-07-05T02:44:12.581553+00:00","updated_at":"2026-07-05T02:44:12.581553+00:00"}