{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:3HOUD2QE5MI4P7JE63VR4ELF3D","short_pith_number":"pith:3HOUD2QE","canonical_record":{"source":{"id":"1604.01350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-05T18:00:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1230803a8985e4e693912bd8437e49816c53ed267d71194caf1c51f9ac19b50a","abstract_canon_sha256":"be2a2e85c5af9498920201b7d93d105db51b5465b8d13a56ab249a13bbaf5f56"},"schema_version":"1.0"},"canonical_sha256":"d9dd41ea04eb11c7fd24f6eb1e1165d8fa75235aee864faf0ab2af61b8e117cf","source":{"kind":"arxiv","id":"1604.01350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.01350","created_at":"2026-05-18T01:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"1604.01350v1","created_at":"2026-05-18T01:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01350","created_at":"2026-05-18T01:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"3HOUD2QE5MI4","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3HOUD2QE5MI4P7JE","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3HOUD2QE","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:3HOUD2QE5MI4P7JE63VR4ELF3D","target":"record","payload":{"canonical_record":{"source":{"id":"1604.01350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-05T18:00:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1230803a8985e4e693912bd8437e49816c53ed267d71194caf1c51f9ac19b50a","abstract_canon_sha256":"be2a2e85c5af9498920201b7d93d105db51b5465b8d13a56ab249a13bbaf5f56"},"schema_version":"1.0"},"canonical_sha256":"d9dd41ea04eb11c7fd24f6eb1e1165d8fa75235aee864faf0ab2af61b8e117cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:38.448278Z","signature_b64":"J5pRU2XjV+QK1lN4R0aKHZv/LhnckNMJArgueMztx+7sXCXH3g+fhh9GcpNSSWB6+Z1zWWGVlOcUWGqsqtddDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9dd41ea04eb11c7fd24f6eb1e1165d8fa75235aee864faf0ab2af61b8e117cf","last_reissued_at":"2026-05-18T01:17:38.447626Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:38.447626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.01350","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aJ37ceTqfWMM5KDWLb26NXzKVbLsZunfTuH+MjH+i6Nl4/t4tfKgqbX2BXWZXaVkxSlEzsD7zPtpELiGnRZSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:52:01.058608Z"},"content_sha256":"8ad64efa93a37d4f426b9dcb5e7828bd99c4d8349a2381f119e88433bc343765","schema_version":"1.0","event_id":"sha256:8ad64efa93a37d4f426b9dcb5e7828bd99c4d8349a2381f119e88433bc343765"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:3HOUD2QE5MI4P7JE63VR4ELF3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bounded Optimal Exploration in MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Kenji Kawaguchi","submitted_at":"2016-04-05T18:00:02Z","abstract_excerpt":"Within the framework of probably approximately correct Markov decision processes (PAC-MDP), much theoretical work has focused on methods to attain near optimality after a relatively long period of learning and exploration. However, practical concerns require the attainment of satisfactory behavior within a short period of time. In this paper, we relax the PAC-MDP conditions to reconcile theoretically driven exploration methods and practical needs. We propose simple algorithms for discrete and continuous state spaces, and illustrate the benefits of our proposed relaxation via theoretical analys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01350","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oJnVICfergSwwFwyrwRz/lSb+5oZwPiC69Mn18OVX204FTUOIBX9/LpmktpTkQNPWL96XEKerY9rN2swlYB7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:52:01.059252Z"},"content_sha256":"a5b147de78c4d644ffdbd16d9a63423cfccb445bf7246f9ee3e3b5f2671a591a","schema_version":"1.0","event_id":"sha256:a5b147de78c4d644ffdbd16d9a63423cfccb445bf7246f9ee3e3b5f2671a591a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HOUD2QE5MI4P7JE63VR4ELF3D/bundle.json","state_url":"https://pith.science/pith/3HOUD2QE5MI4P7JE63VR4ELF3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HOUD2QE5MI4P7JE63VR4ELF3D/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":"2026-06-07T17:52:01Z","links":{"resolver":"https://pith.science/pith/3HOUD2QE5MI4P7JE63VR4ELF3D","bundle":"https://pith.science/pith/3HOUD2QE5MI4P7JE63VR4ELF3D/bundle.json","state":"https://pith.science/pith/3HOUD2QE5MI4P7JE63VR4ELF3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HOUD2QE5MI4P7JE63VR4ELF3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:3HOUD2QE5MI4P7JE63VR4ELF3D","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":"be2a2e85c5af9498920201b7d93d105db51b5465b8d13a56ab249a13bbaf5f56","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-05T18:00:02Z","title_canon_sha256":"1230803a8985e4e693912bd8437e49816c53ed267d71194caf1c51f9ac19b50a"},"schema_version":"1.0","source":{"id":"1604.01350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.01350","created_at":"2026-05-18T01:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"1604.01350v1","created_at":"2026-05-18T01:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01350","created_at":"2026-05-18T01:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"3HOUD2QE5MI4","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3HOUD2QE5MI4P7JE","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3HOUD2QE","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:a5b147de78c4d644ffdbd16d9a63423cfccb445bf7246f9ee3e3b5f2671a591a","target":"graph","created_at":"2026-05-18T01:17:38Z","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":"Within the framework of probably approximately correct Markov decision processes (PAC-MDP), much theoretical work has focused on methods to attain near optimality after a relatively long period of learning and exploration. However, practical concerns require the attainment of satisfactory behavior within a short period of time. In this paper, we relax the PAC-MDP conditions to reconcile theoretically driven exploration methods and practical needs. We propose simple algorithms for discrete and continuous state spaces, and illustrate the benefits of our proposed relaxation via theoretical analys","authors_text":"Kenji Kawaguchi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-05T18:00:02Z","title":"Bounded Optimal Exploration in MDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01350","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":"sha256:8ad64efa93a37d4f426b9dcb5e7828bd99c4d8349a2381f119e88433bc343765","target":"record","created_at":"2026-05-18T01:17:38Z","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":"be2a2e85c5af9498920201b7d93d105db51b5465b8d13a56ab249a13bbaf5f56","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-05T18:00:02Z","title_canon_sha256":"1230803a8985e4e693912bd8437e49816c53ed267d71194caf1c51f9ac19b50a"},"schema_version":"1.0","source":{"id":"1604.01350","kind":"arxiv","version":1}},"canonical_sha256":"d9dd41ea04eb11c7fd24f6eb1e1165d8fa75235aee864faf0ab2af61b8e117cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9dd41ea04eb11c7fd24f6eb1e1165d8fa75235aee864faf0ab2af61b8e117cf","first_computed_at":"2026-05-18T01:17:38.447626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:38.447626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J5pRU2XjV+QK1lN4R0aKHZv/LhnckNMJArgueMztx+7sXCXH3g+fhh9GcpNSSWB6+Z1zWWGVlOcUWGqsqtddDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:38.448278Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.01350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ad64efa93a37d4f426b9dcb5e7828bd99c4d8349a2381f119e88433bc343765","sha256:a5b147de78c4d644ffdbd16d9a63423cfccb445bf7246f9ee3e3b5f2671a591a"],"state_sha256":"9f6810722c0ae2005c9f88b91ce198cf9945d6186e5f85ec826356e879adb993"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eu7+n387ZQwu8oJ03rsAZB6mYoTGQo42T4xZtEG/WuDOW9KqZkMJ9KPGXHSqWJcHG0sHSyTSpOmXusMS/8IJBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T17:52:01.063112Z","bundle_sha256":"da8b176a8faf18d7d99d17588ce8a9de73df15c33da7a3580f659f3b8d986635"}}