{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:6B3P3IF2SWMLDHXLBIBGZEWW62","short_pith_number":"pith:6B3P3IF2","schema_version":"1.0","canonical_sha256":"f076fda0ba9598b19eeb0a026c92d6f6a6eda2bc9144ae3e0c1810f59f03513c","source":{"kind":"arxiv","id":"1608.02732","version":1},"attestation_state":"computed","paper":{"title":"On Lower Bounds for Regret in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2016-08-09T09:02:01Z","abstract_excerpt":"This is a brief technical note to clarify the state of lower bounds on regret for reinforcement learning. In particular, this paper:\n  - Reproduces a lower bound on regret for reinforcement learning, similar to the result of Theorem 5 in the journal UCRL2 paper (Jaksch et al 2010).\n  - Clarifies that the proposed proof of Theorem 6 in the REGAL paper (Bartlett and Tewari 2009) does not hold using the standard techniques without further work. We suggest that this result should instead be considered a conjecture as it has no rigorous proof.\n  - Suggests that the conjectured lower bound given by "},"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":"1608.02732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:02:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d79177e2d93ddbb0a785578b5892224324a5a7d4d069048c31000a02497daf91","abstract_canon_sha256":"7c1df11f2647d3a845e52c4cd1bf05ece59bc94f16a80e0e8f89c80f2b80c006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:33.801304Z","signature_b64":"wwt/p01GdJtMXxklHy1DkRLNRflQnDfatq6TcIa6YjiRAuyNtl3cJ1jZIGZqVox2Zc7v36e4r2xxA8YHnXw7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f076fda0ba9598b19eeb0a026c92d6f6a6eda2bc9144ae3e0c1810f59f03513c","last_reissued_at":"2026-05-18T01:09:33.800856Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:33.800856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Lower Bounds for Regret in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2016-08-09T09:02:01Z","abstract_excerpt":"This is a brief technical note to clarify the state of lower bounds on regret for reinforcement learning. In particular, this paper:\n  - Reproduces a lower bound on regret for reinforcement learning, similar to the result of Theorem 5 in the journal UCRL2 paper (Jaksch et al 2010).\n  - Clarifies that the proposed proof of Theorem 6 in the REGAL paper (Bartlett and Tewari 2009) does not hold using the standard techniques without further work. We suggest that this result should instead be considered a conjecture as it has no rigorous proof.\n  - Suggests that the conjectured lower bound given by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02732","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1608.02732","created_at":"2026-05-18T01:09:33.800923+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.02732v1","created_at":"2026-05-18T01:09:33.800923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02732","created_at":"2026-05-18T01:09:33.800923+00:00"},{"alias_kind":"pith_short_12","alias_value":"6B3P3IF2SWML","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"6B3P3IF2SWMLDHXL","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"6B3P3IF2","created_at":"2026-05-18T12:30:01.593930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21214","citing_title":"Behavior-Consistent Deep Reinforcement Learning","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21214","citing_title":"Behavior-Consistent Deep Reinforcement Learning","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62","json":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62.json","graph_json":"https://pith.science/api/pith-number/6B3P3IF2SWMLDHXLBIBGZEWW62/graph.json","events_json":"https://pith.science/api/pith-number/6B3P3IF2SWMLDHXLBIBGZEWW62/events.json","paper":"https://pith.science/paper/6B3P3IF2"},"agent_actions":{"view_html":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62","download_json":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62.json","view_paper":"https://pith.science/paper/6B3P3IF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.02732&json=true","fetch_graph":"https://pith.science/api/pith-number/6B3P3IF2SWMLDHXLBIBGZEWW62/graph.json","fetch_events":"https://pith.science/api/pith-number/6B3P3IF2SWMLDHXLBIBGZEWW62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62/action/storage_attestation","attest_author":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62/action/author_attestation","sign_citation":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62/action/citation_signature","submit_replication":"https://pith.science/pith/6B3P3IF2SWMLDHXLBIBGZEWW62/action/replication_record"}},"created_at":"2026-05-18T01:09:33.800923+00:00","updated_at":"2026-05-18T01:09:33.800923+00:00"}