{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SSOLOD57GWJY3DW2FDB42UZM7D","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":"55d1282cacf84162d7cf35d625397c703d299bf01e92306168a5e35fca57f9c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-05-28T15:36:01Z","title_canon_sha256":"205cd03febab8089cd77a5891df1aebf2a702b0c5487f080215d3130fd15eaca"},"schema_version":"1.0","source":{"id":"2105.13919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13919","created_at":"2026-07-05T02:44:12Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13919v1","created_at":"2026-07-05T02:44:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13919","created_at":"2026-07-05T02:44:12Z"},{"alias_kind":"pith_short_12","alias_value":"SSOLOD57GWJY","created_at":"2026-07-05T02:44:12Z"},{"alias_kind":"pith_short_16","alias_value":"SSOLOD57GWJY3DW2","created_at":"2026-07-05T02:44:12Z"},{"alias_kind":"pith_short_8","alias_value":"SSOLOD57","created_at":"2026-07-05T02:44:12Z"}],"graph_snapshots":[{"event_id":"sha256:0d6af50d1d8dc3efa3f1ad2332db94c01f5d08a001d93ac34376c2fc5e7ac468","target":"graph","created_at":"2026-07-05T02:44:12Z","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/2105.13919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Rahul Singh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-05-28T15:36:01Z","title":"Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13919","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":"sha256:515ed204f1a60c051a2a2aa87abdb24e10bf294ff82879a43727b78940f0e1ba","target":"record","created_at":"2026-07-05T02:44:12Z","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":"55d1282cacf84162d7cf35d625397c703d299bf01e92306168a5e35fca57f9c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-05-28T15:36:01Z","title_canon_sha256":"205cd03febab8089cd77a5891df1aebf2a702b0c5487f080215d3130fd15eaca"},"schema_version":"1.0","source":{"id":"2105.13919","kind":"arxiv","version":1}},"canonical_sha256":"949cb70fbf35938d8eda28c3cd532cf8d3f67002d9a8c4929f015dac1bc80bae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"949cb70fbf35938d8eda28c3cd532cf8d3f67002d9a8c4929f015dac1bc80bae","first_computed_at":"2026-07-05T02:44:12.581487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:12.581487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9+dceOSbW8jaBmEVJtKPEISFylgaoZ2CzUHZym7DIv72vABIGHwSkimu/2st2bEcUPCmcnGVJBcVYz/dnoj5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:12.581875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.13919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:515ed204f1a60c051a2a2aa87abdb24e10bf294ff82879a43727b78940f0e1ba","sha256:0d6af50d1d8dc3efa3f1ad2332db94c01f5d08a001d93ac34376c2fc5e7ac468"],"state_sha256":"bc54171284634c8b1d42ff82f62606855d0b64cc12f9dba98c78631658917ad7"}