{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4VIA7LBBIJAKYMT35U455FM6QN","short_pith_number":"pith:4VIA7LBB","schema_version":"1.0","canonical_sha256":"e5500fac214240ac327bed39de959e8360daa71e2ec05a7e20a8ed521825c19a","source":{"kind":"arxiv","id":"1808.00888","version":1},"attestation_state":"computed","paper":{"title":"Estimation and Control Using Sampling-Based Bayesian Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Mykel J. Kochenderfer, Patrick Slade, Zachary N. Sunberg","submitted_at":"2018-08-01T01:55:37Z","abstract_excerpt":"Real-world autonomous systems operate under uncertainty about both their pose and dynamics. Autonomous control systems must simultaneously perform estimation and control tasks to maintain robustness to changing dynamics or modeling errors. However, information gathering actions often conflict with optimal actions for reaching control objectives, requiring a trade-off between exploration and exploitation. The specific problem setting considered here is for discrete-time nonlinear systems, with process noise, input-constraints, and parameter uncertainty. This article frames this problem as a Bay"},"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":"1808.00888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-08-01T01:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"7bc9cebac087cebdb28302f68b3fb1f69f5c6be33ea6b7108bd8d72d12e060d2","abstract_canon_sha256":"cad33e212ae697da1e11cf8c7abb6ab590aa24cab6c31e4b05fc50b367aabe38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:01.113351Z","signature_b64":"5szvhkSRAETPjuKrHG5bLBCiGvzFx0qFX0cdS02QhxeZLT/USBbLq9BA1B73zG0ymN+tkKIWeq60yK3PwhAADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5500fac214240ac327bed39de959e8360daa71e2ec05a7e20a8ed521825c19a","last_reissued_at":"2026-05-18T00:09:01.112734Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:01.112734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimation and Control Using Sampling-Based Bayesian Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Mykel J. Kochenderfer, Patrick Slade, Zachary N. Sunberg","submitted_at":"2018-08-01T01:55:37Z","abstract_excerpt":"Real-world autonomous systems operate under uncertainty about both their pose and dynamics. Autonomous control systems must simultaneously perform estimation and control tasks to maintain robustness to changing dynamics or modeling errors. However, information gathering actions often conflict with optimal actions for reaching control objectives, requiring a trade-off between exploration and exploitation. The specific problem setting considered here is for discrete-time nonlinear systems, with process noise, input-constraints, and parameter uncertainty. This article frames this problem as a Bay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00888","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":"1808.00888","created_at":"2026-05-18T00:09:01.112819+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.00888v1","created_at":"2026-05-18T00:09:01.112819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00888","created_at":"2026-05-18T00:09:01.112819+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VIA7LBBIJAK","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VIA7LBBIJAKYMT3","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VIA7LBB","created_at":"2026-05-18T12:32:05.422762+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/4VIA7LBBIJAKYMT35U455FM6QN","json":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN.json","graph_json":"https://pith.science/api/pith-number/4VIA7LBBIJAKYMT35U455FM6QN/graph.json","events_json":"https://pith.science/api/pith-number/4VIA7LBBIJAKYMT35U455FM6QN/events.json","paper":"https://pith.science/paper/4VIA7LBB"},"agent_actions":{"view_html":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN","download_json":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN.json","view_paper":"https://pith.science/paper/4VIA7LBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.00888&json=true","fetch_graph":"https://pith.science/api/pith-number/4VIA7LBBIJAKYMT35U455FM6QN/graph.json","fetch_events":"https://pith.science/api/pith-number/4VIA7LBBIJAKYMT35U455FM6QN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN/action/storage_attestation","attest_author":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN/action/author_attestation","sign_citation":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN/action/citation_signature","submit_replication":"https://pith.science/pith/4VIA7LBBIJAKYMT35U455FM6QN/action/replication_record"}},"created_at":"2026-05-18T00:09:01.112819+00:00","updated_at":"2026-05-18T00:09:01.112819+00:00"}