{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NK3THGVIK6YUUWUAKYSY5DAUQW","short_pith_number":"pith:NK3THGVI","canonical_record":{"source":{"id":"1802.04020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T12:58:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8d1cc3fe95a82636ce1fd0f8efd7d9fd185c582f2265608a64593d85594da582","abstract_canon_sha256":"39e548f1e849d802538765f8bbcb7771e99e9f86a2a93dd913d2f29e1b49a435"},"schema_version":"1.0"},"canonical_sha256":"6ab7339aa857b14a5a8056258e8c1485a4c65ef5f2142ae2782b6efab483f65a","source":{"kind":"arxiv","id":"1802.04020","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04020","created_at":"2026-05-18T00:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04020v2","created_at":"2026-05-18T00:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04020","created_at":"2026-05-18T00:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"NK3THGVIK6YU","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NK3THGVIK6YUUWUA","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NK3THGVI","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NK3THGVIK6YUUWUAKYSY5DAUQW","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T12:58:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8d1cc3fe95a82636ce1fd0f8efd7d9fd185c582f2265608a64593d85594da582","abstract_canon_sha256":"39e548f1e849d802538765f8bbcb7771e99e9f86a2a93dd913d2f29e1b49a435"},"schema_version":"1.0"},"canonical_sha256":"6ab7339aa857b14a5a8056258e8c1485a4c65ef5f2142ae2782b6efab483f65a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:23.506725Z","signature_b64":"8JlSPW2IN67alng+h2iIwikBkzPYSsbpgpVPVDgBNboMv/cBIR2lalPBsko6eK0+13Dcq0Y0Ra2fPf1LEwSGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ab7339aa857b14a5a8056258e8c1485a4c65ef5f2142ae2782b6efab483f65a","last_reissued_at":"2026-05-18T00:11:23.506118Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:23.506118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04020","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5k5mz1uYbbjUeP+P+nJ8CPq8pi4wlPUMXjyXV9wGByqdVszcewBtDkGPGijVd79GO9Fn4n7snRBsvK2wxtqTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:14:51.737027Z"},"content_sha256":"940f55a438f3811ccf0ea887df5f7b0a8ef4b3aa2880ac3ebe3d116afe993278","schema_version":"1.0","event_id":"sha256:940f55a438f3811ccf0ea887df5f7b0a8ef4b3aa2880ac3ebe3d116afe993278"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NK3THGVIK6YUUWUAKYSY5DAUQW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Matteo Pirotta, Ronald Ortner, Ronan Fruit","submitted_at":"2018-02-12T12:58:45Z","abstract_excerpt":"We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov decision process (MDP) for which an upper bound $c$ on the span of the optimal bias function is known. For an MDP with $S$ states, $A$ actions and $\\Gamma \\leq S$ possible next states, we prove a regret bound of $\\widetilde{O}(c\\sqrt{\\Gamma SAT})$, which significantly improves over existing algorithms (e.g., UCRL and PSRL), whose regret scales linearly with the MDP diameter $D$. In fact, the optimal bias span is finite and often much smaller than $D$ (e.g., $D=\\inft"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04020","kind":"arxiv","version":2},"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":"2026-05-18T00:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zq3VIZXpHwxUUITHW9wYMJXNH9TU7oPR4duU+IWAer97cQ+Y1EhyVn4dTbdvmA85zot0mIOPrEuNATSt/bN3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:14:51.737381Z"},"content_sha256":"8b74ea6987318df428ae3b689619ef8a18cb558030e6f1b21640bde50c9bc0cc","schema_version":"1.0","event_id":"sha256:8b74ea6987318df428ae3b689619ef8a18cb558030e6f1b21640bde50c9bc0cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NK3THGVIK6YUUWUAKYSY5DAUQW/bundle.json","state_url":"https://pith.science/pith/NK3THGVIK6YUUWUAKYSY5DAUQW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NK3THGVIK6YUUWUAKYSY5DAUQW/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":"2026-06-06T09:14:51Z","links":{"resolver":"https://pith.science/pith/NK3THGVIK6YUUWUAKYSY5DAUQW","bundle":"https://pith.science/pith/NK3THGVIK6YUUWUAKYSY5DAUQW/bundle.json","state":"https://pith.science/pith/NK3THGVIK6YUUWUAKYSY5DAUQW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NK3THGVIK6YUUWUAKYSY5DAUQW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NK3THGVIK6YUUWUAKYSY5DAUQW","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":"39e548f1e849d802538765f8bbcb7771e99e9f86a2a93dd913d2f29e1b49a435","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T12:58:45Z","title_canon_sha256":"8d1cc3fe95a82636ce1fd0f8efd7d9fd185c582f2265608a64593d85594da582"},"schema_version":"1.0","source":{"id":"1802.04020","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04020","created_at":"2026-05-18T00:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04020v2","created_at":"2026-05-18T00:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04020","created_at":"2026-05-18T00:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"NK3THGVIK6YU","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NK3THGVIK6YUUWUA","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NK3THGVI","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:8b74ea6987318df428ae3b689619ef8a18cb558030e6f1b21640bde50c9bc0cc","target":"graph","created_at":"2026-05-18T00:11:23Z","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":"We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov decision process (MDP) for which an upper bound $c$ on the span of the optimal bias function is known. For an MDP with $S$ states, $A$ actions and $\\Gamma \\leq S$ possible next states, we prove a regret bound of $\\widetilde{O}(c\\sqrt{\\Gamma SAT})$, which significantly improves over existing algorithms (e.g., UCRL and PSRL), whose regret scales linearly with the MDP diameter $D$. In fact, the optimal bias span is finite and often much smaller than $D$ (e.g., $D=\\inft","authors_text":"Alessandro Lazaric, Matteo Pirotta, Ronald Ortner, Ronan Fruit","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T12:58:45Z","title":"Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04020","kind":"arxiv","version":2},"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":"sha256:940f55a438f3811ccf0ea887df5f7b0a8ef4b3aa2880ac3ebe3d116afe993278","target":"record","created_at":"2026-05-18T00:11:23Z","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":"39e548f1e849d802538765f8bbcb7771e99e9f86a2a93dd913d2f29e1b49a435","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T12:58:45Z","title_canon_sha256":"8d1cc3fe95a82636ce1fd0f8efd7d9fd185c582f2265608a64593d85594da582"},"schema_version":"1.0","source":{"id":"1802.04020","kind":"arxiv","version":2}},"canonical_sha256":"6ab7339aa857b14a5a8056258e8c1485a4c65ef5f2142ae2782b6efab483f65a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ab7339aa857b14a5a8056258e8c1485a4c65ef5f2142ae2782b6efab483f65a","first_computed_at":"2026-05-18T00:11:23.506118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:23.506118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8JlSPW2IN67alng+h2iIwikBkzPYSsbpgpVPVDgBNboMv/cBIR2lalPBsko6eK0+13Dcq0Y0Ra2fPf1LEwSGBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:23.506725Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04020","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:940f55a438f3811ccf0ea887df5f7b0a8ef4b3aa2880ac3ebe3d116afe993278","sha256:8b74ea6987318df428ae3b689619ef8a18cb558030e6f1b21640bde50c9bc0cc"],"state_sha256":"a8ea59cb171778935344a40eff1e56b01b5201db7dee44e4d2efe32b1c1b77b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRa3akhhGIT59r09I4ADOotuLX6PPyQMmQK2pYyR/NoilySL5B5YPmF+Ac+nNywLST3zNzlOBJ70v5E1rIoKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T09:14:51.739237Z","bundle_sha256":"70a628bac928886dea44cd51ab50b9bd7a74d3aeee088c7dfe75e0edf67a0404"}}