{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:D2ZRYHWCKTVZYVWQBL44P276VZ","short_pith_number":"pith:D2ZRYHWC","canonical_record":{"source":{"id":"1004.5229","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-29T09:31:55Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"ea0a9ccfe89bebb1299f58dd84d78444355348965483bd1abffae536239f3e91","abstract_canon_sha256":"0459926e27a62e60dd7ce51e657a8f589cabff0e3bd00672a73cfc19c7e5d8ff"},"schema_version":"1.0"},"canonical_sha256":"1eb31c1ec254eb9c56d00af9c7ebfeae4eb93e4f22c5fe302f4658b0007df2e5","source":{"kind":"arxiv","id":"1004.5229","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1004.5229","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"1004.5229v3","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.5229","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"D2ZRYHWCKTVZ","created_at":"2026-05-18T12:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"D2ZRYHWCKTVZYVWQ","created_at":"2026-05-18T12:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"D2ZRYHWC","created_at":"2026-05-18T12:26:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:D2ZRYHWCKTVZYVWQBL44P276VZ","target":"record","payload":{"canonical_record":{"source":{"id":"1004.5229","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-29T09:31:55Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"ea0a9ccfe89bebb1299f58dd84d78444355348965483bd1abffae536239f3e91","abstract_canon_sha256":"0459926e27a62e60dd7ce51e657a8f589cabff0e3bd00672a73cfc19c7e5d8ff"},"schema_version":"1.0"},"canonical_sha256":"1eb31c1ec254eb9c56d00af9c7ebfeae4eb93e4f22c5fe302f4658b0007df2e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:12:43.062885Z","signature_b64":"KdanyIaHT6m3wKVtmY+YWO1kfCwlsu6sufVAYzo2VdEQaY1xf9cSZpUordf398bP0HawNqwOpUJFgqKF163HBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eb31c1ec254eb9c56d00af9c7ebfeae4eb93e4f22c5fe302f4658b0007df2e5","last_reissued_at":"2026-05-18T04:12:43.062146Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:12:43.062146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1004.5229","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BhsTAzf8CZvZfiy9nhlDvEItJxWJtwgMxb00hUQngGQ+6O2Fozfh5JRbWU7Odwowk4XQ8p3omveNcZrxiE2JBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:36:19.649652Z"},"content_sha256":"0b03960b8f6cef6c5e69e9596a3adadada4bca7b901a4a0738af703aec235fe4","schema_version":"1.0","event_id":"sha256:0b03960b8f6cef6c5e69e9596a3adadada4bca7b901a4a0738af703aec235fe4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:D2ZRYHWCKTVZYVWQBL44P276VZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimism in Reinforcement Learning and Kullback-Leibler Divergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aur\\'elien Garivier (LTCI), Olivier Capp\\'e (LTCI), Sarah Filippi (LTCI)","submitted_at":"2010-04-29T09:31:55Z","abstract_excerpt":"We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint of consistency with the estimated model tran- sition probabilities. The UCRL2 algorithm by Auer, Jaksch and Ortner (2009), which follows this strategy, has recently been shown to guarantee near-optimal regret bounds. In this paper, we strongly argue in favor of using the Kullback-Leibler (KL) divergence for this purpose. By studying the linear maximization pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.5229","kind":"arxiv","version":3},"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":"2026-05-18T04:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xQScuUNRZEYp2n5tlJQIwquZg6VSbKBCy7PRrzyORU4+4ltS9bpbWVlAlNC7worbNONaQVZQtUMZ2gSbG7ShAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:36:19.650041Z"},"content_sha256":"2e5bbf7fd28ae1e902b7a50c9f9780bd989e21d627c1d9889ecf59247b52d5dd","schema_version":"1.0","event_id":"sha256:2e5bbf7fd28ae1e902b7a50c9f9780bd989e21d627c1d9889ecf59247b52d5dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D2ZRYHWCKTVZYVWQBL44P276VZ/bundle.json","state_url":"https://pith.science/pith/D2ZRYHWCKTVZYVWQBL44P276VZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D2ZRYHWCKTVZYVWQBL44P276VZ/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":"2026-05-25T20:36:19Z","links":{"resolver":"https://pith.science/pith/D2ZRYHWCKTVZYVWQBL44P276VZ","bundle":"https://pith.science/pith/D2ZRYHWCKTVZYVWQBL44P276VZ/bundle.json","state":"https://pith.science/pith/D2ZRYHWCKTVZYVWQBL44P276VZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D2ZRYHWCKTVZYVWQBL44P276VZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:D2ZRYHWCKTVZYVWQBL44P276VZ","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":"0459926e27a62e60dd7ce51e657a8f589cabff0e3bd00672a73cfc19c7e5d8ff","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-29T09:31:55Z","title_canon_sha256":"ea0a9ccfe89bebb1299f58dd84d78444355348965483bd1abffae536239f3e91"},"schema_version":"1.0","source":{"id":"1004.5229","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1004.5229","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"1004.5229v3","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.5229","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"D2ZRYHWCKTVZ","created_at":"2026-05-18T12:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"D2ZRYHWCKTVZYVWQ","created_at":"2026-05-18T12:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"D2ZRYHWC","created_at":"2026-05-18T12:26:06Z"}],"graph_snapshots":[{"event_id":"sha256:2e5bbf7fd28ae1e902b7a50c9f9780bd989e21d627c1d9889ecf59247b52d5dd","target":"graph","created_at":"2026-05-18T04:12:43Z","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 consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint of consistency with the estimated model tran- sition probabilities. The UCRL2 algorithm by Auer, Jaksch and Ortner (2009), which follows this strategy, has recently been shown to guarantee near-optimal regret bounds. In this paper, we strongly argue in favor of using the Kullback-Leibler (KL) divergence for this purpose. By studying the linear maximization pr","authors_text":"Aur\\'elien Garivier (LTCI), Olivier Capp\\'e (LTCI), Sarah Filippi (LTCI)","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-29T09:31:55Z","title":"Optimism in Reinforcement Learning and Kullback-Leibler Divergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.5229","kind":"arxiv","version":3},"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":"sha256:0b03960b8f6cef6c5e69e9596a3adadada4bca7b901a4a0738af703aec235fe4","target":"record","created_at":"2026-05-18T04:12:43Z","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":"0459926e27a62e60dd7ce51e657a8f589cabff0e3bd00672a73cfc19c7e5d8ff","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-29T09:31:55Z","title_canon_sha256":"ea0a9ccfe89bebb1299f58dd84d78444355348965483bd1abffae536239f3e91"},"schema_version":"1.0","source":{"id":"1004.5229","kind":"arxiv","version":3}},"canonical_sha256":"1eb31c1ec254eb9c56d00af9c7ebfeae4eb93e4f22c5fe302f4658b0007df2e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1eb31c1ec254eb9c56d00af9c7ebfeae4eb93e4f22c5fe302f4658b0007df2e5","first_computed_at":"2026-05-18T04:12:43.062146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:12:43.062146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KdanyIaHT6m3wKVtmY+YWO1kfCwlsu6sufVAYzo2VdEQaY1xf9cSZpUordf398bP0HawNqwOpUJFgqKF163HBg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:12:43.062885Z","signed_message":"canonical_sha256_bytes"},"source_id":"1004.5229","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b03960b8f6cef6c5e69e9596a3adadada4bca7b901a4a0738af703aec235fe4","sha256:2e5bbf7fd28ae1e902b7a50c9f9780bd989e21d627c1d9889ecf59247b52d5dd"],"state_sha256":"c27a31bf6774472fc56a9a342963e781941b10528210b17e0166aa24e31e3a7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGhD9zp0+luAI+cyi1dpnK8Ba3Ep6/KlK+cWe96FngeDch0SOLRnKZycZLPsoVda+zLg3FHqyshM7kiTwIjEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:36:19.652728Z","bundle_sha256":"24c947d1620d51ff7b4fe7b87aa5d250ce46d08ce3dc53fdf64fa330188bc125"}}