{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2006:IR2KIN2QHE2C62XDMKJHS6P3C6","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":"595195c01406ccbb03bf00d934f5d7bc2a4ec3cbd8ca903b6455c857f5abc01a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2006-04-05T10:29:48Z","title_canon_sha256":"e7b93743ecdd9d67453a033fa8d8bb63ab251abaa323629bbe93e8775c559bdb"},"schema_version":"1.0","source":{"id":"cs/0604010","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0604010","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0604010v2","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0604010","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"IR2KIN2QHE2C","created_at":"2026-05-18T12:25:54Z"},{"alias_kind":"pith_short_16","alias_value":"IR2KIN2QHE2C62XD","created_at":"2026-05-18T12:25:54Z"},{"alias_kind":"pith_short_8","alias_value":"IR2KIN2Q","created_at":"2026-05-18T12:25:54Z"}],"graph_snapshots":[{"event_id":"sha256:06d0e7ea67f91e0e244eeae78ea66726c959f235564b9e6ba7ae806c92d1c455","target":"graph","created_at":"2026-05-18T00:14:11Z","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":"While in general trading off exploration and exploitation in reinforcement learning is hard, under some formulations relatively simple solutions exist. In this paper, we first derive upper bounds for the utility of selecting different actions in the multi-armed bandit setting. Unlike the common statistical upper confidence bounds, these explicitly link the planning horizon, uncertainty and the need for exploration explicit. The resulting algorithm can be seen as a generalisation of the classical Thompson sampling algorithm. We experimentally test these algorithms, as well as $\\epsilon$-greedy ","authors_text":"Christos Dimitrakakis","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2006-04-05T10:29:48Z","title":"Nearly optimal exploration-exploitation decision thresholds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0604010","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":"sha256:912e16e9e4dc110597cb94957eeb3fb23c56d002f73d8774ced6d3c455c34cef","target":"record","created_at":"2026-05-18T00:14:11Z","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":"595195c01406ccbb03bf00d934f5d7bc2a4ec3cbd8ca903b6455c857f5abc01a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2006-04-05T10:29:48Z","title_canon_sha256":"e7b93743ecdd9d67453a033fa8d8bb63ab251abaa323629bbe93e8775c559bdb"},"schema_version":"1.0","source":{"id":"cs/0604010","kind":"arxiv","version":2}},"canonical_sha256":"4474a4375039342f6ae362927979fb178cdaf0b0e778715aee3addfed314c200","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4474a4375039342f6ae362927979fb178cdaf0b0e778715aee3addfed314c200","first_computed_at":"2026-05-18T00:14:11.692053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:11.692053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"04N/IYATJR+nOGRFbY0vz17qu3ddqgy6vjiIsTXefuXucsv1Z6AGbKSxG48Dr5WYa0Ga0kYY9K9420ZKh83BBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:11.692445Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/0604010","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:912e16e9e4dc110597cb94957eeb3fb23c56d002f73d8774ced6d3c455c34cef","sha256:06d0e7ea67f91e0e244eeae78ea66726c959f235564b9e6ba7ae806c92d1c455"],"state_sha256":"fd6d86f6f1aa8b0d0dd47072c09992d2d85ff4bd19a78600a575675d1ed47761"}