{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4DEANPA6VVJZ2J6AAL4YCPHTGA","short_pith_number":"pith:4DEANPA6","canonical_record":{"source":{"id":"1703.05449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-16T01:31:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58128e741541cf1c8bf6d5b8fe61ff473c2ae9a2ed260604d7355da6f3ab6cad","abstract_canon_sha256":"76d4ea69425fca02e9507e905c1b0dcb856733c785ac241d44f210170c3715b0"},"schema_version":"1.0"},"canonical_sha256":"e0c806bc1ead539d27c002f9813cf3301d16106d9863903a02f0f73028b96957","source":{"kind":"arxiv","id":"1703.05449","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05449","created_at":"2026-05-18T00:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05449v2","created_at":"2026-05-18T00:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05449","created_at":"2026-05-18T00:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"4DEANPA6VVJZ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4DEANPA6VVJZ2J6A","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4DEANPA6","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4DEANPA6VVJZ2J6AAL4YCPHTGA","target":"record","payload":{"canonical_record":{"source":{"id":"1703.05449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-16T01:31:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58128e741541cf1c8bf6d5b8fe61ff473c2ae9a2ed260604d7355da6f3ab6cad","abstract_canon_sha256":"76d4ea69425fca02e9507e905c1b0dcb856733c785ac241d44f210170c3715b0"},"schema_version":"1.0"},"canonical_sha256":"e0c806bc1ead539d27c002f9813cf3301d16106d9863903a02f0f73028b96957","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:07.231301Z","signature_b64":"3zjfhApMvV+c2HgvAFkJKSmAjOpkOhMlmlMDUQoImyI97cts3JrIIGRVylI2OjCnn+QOrCCY2ieYef7/neuKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0c806bc1ead539d27c002f9813cf3301d16106d9863903a02f0f73028b96957","last_reissued_at":"2026-05-18T00:41:07.230577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:07.230577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.05449","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":"2026-05-18T00:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gxpptfzmh03GqWAtdWXOBKlmCT72rE/gHccsTj8e/pEKakMR/p6Y2fZQaKCaZUPSFSRa4Xcu5WUgJqsi9t22Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:02:24.706674Z"},"content_sha256":"41a7007d0eb8951c4c459a4f552bce94ec0825beed7af771aefea93205d6a828","schema_version":"1.0","event_id":"sha256:41a7007d0eb8951c4c459a4f552bce94ec0825beed7af771aefea93205d6a828"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4DEANPA6VVJZ2J6AAL4YCPHTGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimax Regret Bounds for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ian Osband, Mohammad Gheshlaghi Azar, R\\'emi Munos","submitted_at":"2017-03-16T01:31:33Z","abstract_excerpt":"We consider the problem of provably optimal exploration in reinforcement learning for finite horizon MDPs. We show that an optimistic modification to value iteration achieves a regret bound of $\\tilde{O}( \\sqrt{HSAT} + H^2S^2A+H\\sqrt{T})$ where $H$ is the time horizon, $S$ the number of states, $A$ the number of actions and $T$ the number of time-steps. This result improves over the best previous known bound $\\tilde{O}(HS \\sqrt{AT})$ achieved by the UCRL2 algorithm of Jaksch et al., 2010. The key significance of our new results is that when $T\\geq H^3S^3A$ and $SA\\geq H$, it leads to a regret "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05449","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":"2026-05-18T00:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z9A60G+Z1zQmhpYH5NLsWlHXTphFlqGm5RV5NNzRZsjjLOR46tBM2JhZlOfA78LNHAMeuEPRi7O5EyTmJZ5cDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:02:24.707378Z"},"content_sha256":"67419c584e97e3ac2247525670006b2cdfd6d1bd5fa9ba11a564290aca2f2222","schema_version":"1.0","event_id":"sha256:67419c584e97e3ac2247525670006b2cdfd6d1bd5fa9ba11a564290aca2f2222"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DEANPA6VVJZ2J6AAL4YCPHTGA/bundle.json","state_url":"https://pith.science/pith/4DEANPA6VVJZ2J6AAL4YCPHTGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DEANPA6VVJZ2J6AAL4YCPHTGA/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":"2026-06-10T09:02:24Z","links":{"resolver":"https://pith.science/pith/4DEANPA6VVJZ2J6AAL4YCPHTGA","bundle":"https://pith.science/pith/4DEANPA6VVJZ2J6AAL4YCPHTGA/bundle.json","state":"https://pith.science/pith/4DEANPA6VVJZ2J6AAL4YCPHTGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DEANPA6VVJZ2J6AAL4YCPHTGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4DEANPA6VVJZ2J6AAL4YCPHTGA","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":"76d4ea69425fca02e9507e905c1b0dcb856733c785ac241d44f210170c3715b0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-16T01:31:33Z","title_canon_sha256":"58128e741541cf1c8bf6d5b8fe61ff473c2ae9a2ed260604d7355da6f3ab6cad"},"schema_version":"1.0","source":{"id":"1703.05449","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05449","created_at":"2026-05-18T00:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05449v2","created_at":"2026-05-18T00:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05449","created_at":"2026-05-18T00:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"4DEANPA6VVJZ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4DEANPA6VVJZ2J6A","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4DEANPA6","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:67419c584e97e3ac2247525670006b2cdfd6d1bd5fa9ba11a564290aca2f2222","target":"graph","created_at":"2026-05-18T00:41:07Z","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 the problem of provably optimal exploration in reinforcement learning for finite horizon MDPs. We show that an optimistic modification to value iteration achieves a regret bound of $\\tilde{O}( \\sqrt{HSAT} + H^2S^2A+H\\sqrt{T})$ where $H$ is the time horizon, $S$ the number of states, $A$ the number of actions and $T$ the number of time-steps. This result improves over the best previous known bound $\\tilde{O}(HS \\sqrt{AT})$ achieved by the UCRL2 algorithm of Jaksch et al., 2010. The key significance of our new results is that when $T\\geq H^3S^3A$ and $SA\\geq H$, it leads to a regret ","authors_text":"Ian Osband, Mohammad Gheshlaghi Azar, R\\'emi Munos","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-16T01:31:33Z","title":"Minimax Regret Bounds for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05449","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":"sha256:41a7007d0eb8951c4c459a4f552bce94ec0825beed7af771aefea93205d6a828","target":"record","created_at":"2026-05-18T00:41:07Z","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":"76d4ea69425fca02e9507e905c1b0dcb856733c785ac241d44f210170c3715b0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-16T01:31:33Z","title_canon_sha256":"58128e741541cf1c8bf6d5b8fe61ff473c2ae9a2ed260604d7355da6f3ab6cad"},"schema_version":"1.0","source":{"id":"1703.05449","kind":"arxiv","version":2}},"canonical_sha256":"e0c806bc1ead539d27c002f9813cf3301d16106d9863903a02f0f73028b96957","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0c806bc1ead539d27c002f9813cf3301d16106d9863903a02f0f73028b96957","first_computed_at":"2026-05-18T00:41:07.230577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:07.230577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3zjfhApMvV+c2HgvAFkJKSmAjOpkOhMlmlMDUQoImyI97cts3JrIIGRVylI2OjCnn+QOrCCY2ieYef7/neuKDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:07.231301Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.05449","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41a7007d0eb8951c4c459a4f552bce94ec0825beed7af771aefea93205d6a828","sha256:67419c584e97e3ac2247525670006b2cdfd6d1bd5fa9ba11a564290aca2f2222"],"state_sha256":"c44a923ee543cb9a7ae94a44e7e7a6fb6328dc1059b954e6868cc4fe5562df15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbEwpNOJAJWy839JA1KcGs1RaQaxmwFf7gNAMalL3aR5Nr/fpjNXnhy8Rz2+AbRASGYCiKEaswe+gJuCDmORDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T09:02:24.711680Z","bundle_sha256":"c98c6e0728ee3f593dd2fcfbbc229d1fc5d60d16cfd47f532c3ebf0a19480ae3"}}