{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TDNE3EFGKNIC3ZZBDTUQWVXCKM","short_pith_number":"pith:TDNE3EFG","schema_version":"1.0","canonical_sha256":"98da4d90a653502de7211ce90b56e2532adf5d9a49572c54167b0e8ce84554de","source":{"kind":"arxiv","id":"1810.01014","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Policy Optimization for Model Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aditya Mandalika, Brian Hou, Gilwoo Lee, Jeongseok Lee, Sanjiban Choudhury, Siddhartha S. Srinivasa","submitted_at":"2018-10-01T23:39:25Z","abstract_excerpt":"Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent maintains a posterior distribution over latent model parameters given a history of observations and maximizes its expected long-term reward with respect to this belief distribution. Our algorithm, Bayesian Policy Optimization, builds on recent policy optimization algorithms to learn a universal policy that navigates the exploration-exploitation trade-off to maximize the Bayesia"},"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":"1810.01014","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-10-01T23:39:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8a7823b077ca7428fb14502354011970338828ca7a3c7301ff7edac22a4504e6","abstract_canon_sha256":"188a8f91e642b294904afebee2b67ee534ccb33e2099f75fe100c83ec5ac47d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:46.089714Z","signature_b64":"3dxQ4aRSSwzRhAMowV07cZ9KI4bsLhj4GQeNhYRW+waQOul697lc5rZ8ttfpWxPf5jPk5gSFRviynjGn/XQoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98da4d90a653502de7211ce90b56e2532adf5d9a49572c54167b0e8ce84554de","last_reissued_at":"2026-05-17T23:46:46.089191Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:46.089191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Policy Optimization for Model Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aditya Mandalika, Brian Hou, Gilwoo Lee, Jeongseok Lee, Sanjiban Choudhury, Siddhartha S. Srinivasa","submitted_at":"2018-10-01T23:39:25Z","abstract_excerpt":"Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent maintains a posterior distribution over latent model parameters given a history of observations and maximizes its expected long-term reward with respect to this belief distribution. Our algorithm, Bayesian Policy Optimization, builds on recent policy optimization algorithms to learn a universal policy that navigates the exploration-exploitation trade-off to maximize the Bayesia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01014","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1810.01014","created_at":"2026-05-17T23:46:46.089272+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01014v2","created_at":"2026-05-17T23:46:46.089272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01014","created_at":"2026-05-17T23:46:46.089272+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDNE3EFGKNIC","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDNE3EFGKNIC3ZZB","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDNE3EFG","created_at":"2026-05-18T12:32:53.628368+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/TDNE3EFGKNIC3ZZBDTUQWVXCKM","json":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM.json","graph_json":"https://pith.science/api/pith-number/TDNE3EFGKNIC3ZZBDTUQWVXCKM/graph.json","events_json":"https://pith.science/api/pith-number/TDNE3EFGKNIC3ZZBDTUQWVXCKM/events.json","paper":"https://pith.science/paper/TDNE3EFG"},"agent_actions":{"view_html":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM","download_json":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM.json","view_paper":"https://pith.science/paper/TDNE3EFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01014&json=true","fetch_graph":"https://pith.science/api/pith-number/TDNE3EFGKNIC3ZZBDTUQWVXCKM/graph.json","fetch_events":"https://pith.science/api/pith-number/TDNE3EFGKNIC3ZZBDTUQWVXCKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/action/storage_attestation","attest_author":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/action/author_attestation","sign_citation":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/action/citation_signature","submit_replication":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/action/replication_record"}},"created_at":"2026-05-17T23:46:46.089272+00:00","updated_at":"2026-05-17T23:46:46.089272+00:00"}