{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EHNKYTOFNNLL4O7HIPRT5TNW4G","short_pith_number":"pith:EHNKYTOF","canonical_record":{"source":{"id":"1803.01626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T12:23:42Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"b7ae9bf273b170e9e65b8b2d43ef0b79bf6b6464f4b900f40f54d8ab074299de","abstract_canon_sha256":"4dd1fbf9ec20d56acb797232d026faced7c1dc0a28613dac153ce1ab0c5e84e5"},"schema_version":"1.0"},"canonical_sha256":"21daac4dc56b56be3be743e33ecdb6e1a51b60c928838e310ab7209d6506904b","source":{"kind":"arxiv","id":"1803.01626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01626","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01626v1","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01626","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"EHNKYTOFNNLL","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EHNKYTOFNNLL4O7H","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EHNKYTOF","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EHNKYTOFNNLL4O7HIPRT5TNW4G","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T12:23:42Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"b7ae9bf273b170e9e65b8b2d43ef0b79bf6b6464f4b900f40f54d8ab074299de","abstract_canon_sha256":"4dd1fbf9ec20d56acb797232d026faced7c1dc0a28613dac153ce1ab0c5e84e5"},"schema_version":"1.0"},"canonical_sha256":"21daac4dc56b56be3be743e33ecdb6e1a51b60c928838e310ab7209d6506904b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:00.067947Z","signature_b64":"gu5Qz/JX2Q6255JDb3lznsiJHiX4eT1pJr9aR8l91rC27yAGAJanq3OioytPfh2N3OdIOBEjkzmw7MMucvMDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21daac4dc56b56be3be743e33ecdb6e1a51b60c928838e310ab7209d6506904b","last_reissued_at":"2026-05-18T00:22:00.067252Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:00.067252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01626","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEo3IZcUFBUEjKYx3kbt5IzTOhod3ObT0py+anVtC56ZumtLUJOx25mNrnMpqQqTXx7h7caZ2bTnP2oTX8PYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:08:38.626401Z"},"content_sha256":"6965eab91d144a93afb1cf687f3b50fdce185d5f69f246bc5c50d7f088da2fb5","schema_version":"1.0","event_id":"sha256:6965eab91d144a93afb1cf687f3b50fdce185d5f69f246bc5c50d7f088da2fb5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EHNKYTOFNNLL4O7HIPRT5TNW4G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"stat.ML","authors_text":"Mohammad Sadegh Talebi, Odalric-Ambrym Maillard","submitted_at":"2018-03-05T12:23:42Z","abstract_excerpt":"The problem of reinforcement learning in an unknown and discrete Markov Decision Process (MDP) under the average-reward criterion is considered, when the learner interacts with the system in a single stream of observations, starting from an initial state without any reset. We revisit the minimax lower bound for that problem by making appear the local variance of the bias function in place of the diameter of the MDP. Furthermore, we provide a novel analysis of the KL-UCRL algorithm establishing a high-probability regret bound scaling as $\\widetilde {\\mathcal O}\\Bigl({\\textstyle \\sqrt{S\\sum_{s,a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01626","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xfHzFKJcYq3O5z2Xyx+ddGALDjlAV/nzd/J/bS3Tb/CHFFk77ISygVqtlEqt1IYOIBkULQAwJEep6kBBreYxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:08:38.627134Z"},"content_sha256":"4cf8617f56e258aeceb7cbd92404ee4733e55ff5bec79d996a378136b0e5768e","schema_version":"1.0","event_id":"sha256:4cf8617f56e258aeceb7cbd92404ee4733e55ff5bec79d996a378136b0e5768e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EHNKYTOFNNLL4O7HIPRT5TNW4G/bundle.json","state_url":"https://pith.science/pith/EHNKYTOFNNLL4O7HIPRT5TNW4G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EHNKYTOFNNLL4O7HIPRT5TNW4G/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T23:08:38Z","links":{"resolver":"https://pith.science/pith/EHNKYTOFNNLL4O7HIPRT5TNW4G","bundle":"https://pith.science/pith/EHNKYTOFNNLL4O7HIPRT5TNW4G/bundle.json","state":"https://pith.science/pith/EHNKYTOFNNLL4O7HIPRT5TNW4G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EHNKYTOFNNLL4O7HIPRT5TNW4G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EHNKYTOFNNLL4O7HIPRT5TNW4G","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":"4dd1fbf9ec20d56acb797232d026faced7c1dc0a28613dac153ce1ab0c5e84e5","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T12:23:42Z","title_canon_sha256":"b7ae9bf273b170e9e65b8b2d43ef0b79bf6b6464f4b900f40f54d8ab074299de"},"schema_version":"1.0","source":{"id":"1803.01626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01626","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01626v1","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01626","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"EHNKYTOFNNLL","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EHNKYTOFNNLL4O7H","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EHNKYTOF","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:4cf8617f56e258aeceb7cbd92404ee4733e55ff5bec79d996a378136b0e5768e","target":"graph","created_at":"2026-05-18T00:22:00Z","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"},"paper":{"abstract_excerpt":"The problem of reinforcement learning in an unknown and discrete Markov Decision Process (MDP) under the average-reward criterion is considered, when the learner interacts with the system in a single stream of observations, starting from an initial state without any reset. We revisit the minimax lower bound for that problem by making appear the local variance of the bias function in place of the diameter of the MDP. Furthermore, we provide a novel analysis of the KL-UCRL algorithm establishing a high-probability regret bound scaling as $\\widetilde {\\mathcal O}\\Bigl({\\textstyle \\sqrt{S\\sum_{s,a","authors_text":"Mohammad Sadegh Talebi, Odalric-Ambrym Maillard","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T12:23:42Z","title":"Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01626","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":"sha256:6965eab91d144a93afb1cf687f3b50fdce185d5f69f246bc5c50d7f088da2fb5","target":"record","created_at":"2026-05-18T00:22:00Z","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":"4dd1fbf9ec20d56acb797232d026faced7c1dc0a28613dac153ce1ab0c5e84e5","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T12:23:42Z","title_canon_sha256":"b7ae9bf273b170e9e65b8b2d43ef0b79bf6b6464f4b900f40f54d8ab074299de"},"schema_version":"1.0","source":{"id":"1803.01626","kind":"arxiv","version":1}},"canonical_sha256":"21daac4dc56b56be3be743e33ecdb6e1a51b60c928838e310ab7209d6506904b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21daac4dc56b56be3be743e33ecdb6e1a51b60c928838e310ab7209d6506904b","first_computed_at":"2026-05-18T00:22:00.067252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:00.067252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gu5Qz/JX2Q6255JDb3lznsiJHiX4eT1pJr9aR8l91rC27yAGAJanq3OioytPfh2N3OdIOBEjkzmw7MMucvMDBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:00.067947Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6965eab91d144a93afb1cf687f3b50fdce185d5f69f246bc5c50d7f088da2fb5","sha256:4cf8617f56e258aeceb7cbd92404ee4733e55ff5bec79d996a378136b0e5768e"],"state_sha256":"4c5f990aa4c48461717f595cc55777ddb3b416e4f470ccf0d21f5b3be5b889c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gi+PYuI9DznBsXU3x4fTp6d1O1J9d4k0kCsp9b9NVjtB68E4y62tj98rfclqn8KxNWLIGgUY1REIwDNDgttnCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T23:08:38.630429Z","bundle_sha256":"70bd155b16449b35e22eca1e31f598e37019b99582cc7502c1b5603ae60ffb0b"}}