{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MBMUUXSXYTR4C7QZBC77DMUAMY","short_pith_number":"pith:MBMUUXSX","schema_version":"1.0","canonical_sha256":"60594a5e57c4e3c17e1908bff1b280662e8b7d9fe6ed1c70c240dbeb7743f1e4","source":{"kind":"arxiv","id":"1802.07668","version":1},"attestation_state":"computed","paper":{"title":"A model for system uncertainty in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Michele Palladino, Ryan Murray","submitted_at":"2018-02-21T17:07:06Z","abstract_excerpt":"This work provides a rigorous framework for studying continuous time control problems in uncertain environments. The framework considered models uncertainty in state dynamics as a measure on the space of functions. This measure is considered to change over time as agents learn their environment. This model can be seem as a variant of either Bayesian reinforcement learning or adaptive control. We study necessary conditions for locally optimal trajectories within this model, in particular deriving an appropriate dynamic programming principle and Hamilton-Jacobi equations. This model provides one"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.07668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-21T17:07:06Z","cross_cats_sorted":[],"title_canon_sha256":"7254305d75495cf8e7f25c529f5e4b5d034a1b00005b96fd391d04de77baaca3","abstract_canon_sha256":"4059e5b8634b7dfb97d56a0418c8a982e3ad7c949e4ec14ea06550f3d96c6954"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.675652Z","signature_b64":"SsPKVKnxdPbWmgDycuJs1z83prRy9HD0xiIh8sHufKL+IDU6bJESYdTh7kiloWoqRm5UQ3cP4fdkCHVege3uCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60594a5e57c4e3c17e1908bff1b280662e8b7d9fe6ed1c70c240dbeb7743f1e4","last_reissued_at":"2026-05-18T00:22:49.675257Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.675257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A model for system uncertainty in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Michele Palladino, Ryan Murray","submitted_at":"2018-02-21T17:07:06Z","abstract_excerpt":"This work provides a rigorous framework for studying continuous time control problems in uncertain environments. The framework considered models uncertainty in state dynamics as a measure on the space of functions. This measure is considered to change over time as agents learn their environment. This model can be seem as a variant of either Bayesian reinforcement learning or adaptive control. We study necessary conditions for locally optimal trajectories within this model, in particular deriving an appropriate dynamic programming principle and Hamilton-Jacobi equations. This model provides one"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07668","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.07668","created_at":"2026-05-18T00:22:49.675324+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.07668v1","created_at":"2026-05-18T00:22:49.675324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07668","created_at":"2026-05-18T00:22:49.675324+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBMUUXSXYTR4","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBMUUXSXYTR4C7QZ","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBMUUXSX","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY","json":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY.json","graph_json":"https://pith.science/api/pith-number/MBMUUXSXYTR4C7QZBC77DMUAMY/graph.json","events_json":"https://pith.science/api/pith-number/MBMUUXSXYTR4C7QZBC77DMUAMY/events.json","paper":"https://pith.science/paper/MBMUUXSX"},"agent_actions":{"view_html":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY","download_json":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY.json","view_paper":"https://pith.science/paper/MBMUUXSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.07668&json=true","fetch_graph":"https://pith.science/api/pith-number/MBMUUXSXYTR4C7QZBC77DMUAMY/graph.json","fetch_events":"https://pith.science/api/pith-number/MBMUUXSXYTR4C7QZBC77DMUAMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/action/storage_attestation","attest_author":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/action/author_attestation","sign_citation":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/action/citation_signature","submit_replication":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/action/replication_record"}},"created_at":"2026-05-18T00:22:49.675324+00:00","updated_at":"2026-05-18T00:22:49.675324+00:00"}