{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:6B3P3IF2SWMLDHXLBIBGZEWW62","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":"7c1df11f2647d3a845e52c4cd1bf05ece59bc94f16a80e0e8f89c80f2b80c006","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:02:01Z","title_canon_sha256":"d79177e2d93ddbb0a785578b5892224324a5a7d4d069048c31000a02497daf91"},"schema_version":"1.0","source":{"id":"1608.02732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.02732","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"1608.02732v1","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02732","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"6B3P3IF2SWML","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6B3P3IF2SWMLDHXL","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6B3P3IF2","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:efabba9760fb89478c89d7ecd24a2497f7f1c51ff590fe0308f5ccf97279f44b","target":"graph","created_at":"2026-05-18T01:09:33Z","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":"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 ","authors_text":"Benjamin Van Roy, Ian Osband","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:02:01Z","title":"On Lower Bounds for Regret in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02732","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":"sha256:6bc45249da4c88b028fca156b54514af2ab2faacde86cc20b2106f75e78a74a0","target":"record","created_at":"2026-05-18T01:09:33Z","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":"7c1df11f2647d3a845e52c4cd1bf05ece59bc94f16a80e0e8f89c80f2b80c006","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:02:01Z","title_canon_sha256":"d79177e2d93ddbb0a785578b5892224324a5a7d4d069048c31000a02497daf91"},"schema_version":"1.0","source":{"id":"1608.02732","kind":"arxiv","version":1}},"canonical_sha256":"f076fda0ba9598b19eeb0a026c92d6f6a6eda2bc9144ae3e0c1810f59f03513c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f076fda0ba9598b19eeb0a026c92d6f6a6eda2bc9144ae3e0c1810f59f03513c","first_computed_at":"2026-05-18T01:09:33.800856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:33.800856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wwt/p01GdJtMXxklHy1DkRLNRflQnDfatq6TcIa6YjiRAuyNtl3cJ1jZIGZqVox2Zc7v36e4r2xxA8YHnXw7Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:33.801304Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.02732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bc45249da4c88b028fca156b54514af2ab2faacde86cc20b2106f75e78a74a0","sha256:efabba9760fb89478c89d7ecd24a2497f7f1c51ff590fe0308f5ccf97279f44b"],"state_sha256":"c551b48239756fc7ecbcf66f366ea803c27c94d916cc38f6ff5996995b5472a5"}