{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TDNE3EFGKNIC3ZZBDTUQWVXCKM","short_pith_number":"pith:TDNE3EFG","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"},"canonical_sha256":"98da4d90a653502de7211ce90b56e2532adf5d9a49572c54167b0e8ce84554de","source":{"kind":"arxiv","id":"1810.01014","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01014","created_at":"2026-05-17T23:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01014v2","created_at":"2026-05-17T23:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01014","created_at":"2026-05-17T23:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"TDNE3EFGKNIC","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TDNE3EFGKNIC3ZZB","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TDNE3EFG","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TDNE3EFGKNIC3ZZBDTUQWVXCKM","target":"record","payload":{"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"},"canonical_sha256":"98da4d90a653502de7211ce90b56e2532adf5d9a49572c54167b0e8ce84554de","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"},"source_kind":"arxiv","source_id":"1810.01014","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":"2026-05-17T23:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yXwxBpWuB2lE/lmm0zeGeAqntWvcdLGS7d23xisMwKTUlRymiwoBKGzvZGe2YTf5WBml/09qo2VwOllKkWmHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T00:48:55.719735Z"},"content_sha256":"75e7263d402c1a734c0d1307eb5c6fa5e4d90d129a2cb33495aa05e4d60aaa78","schema_version":"1.0","event_id":"sha256:75e7263d402c1a734c0d1307eb5c6fa5e4d90d129a2cb33495aa05e4d60aaa78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TDNE3EFGKNIC3ZZBDTUQWVXCKM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JryozrIRvAjxYQztJfPr07heCT17qibwAeb4d7DwizOVoyRwnjLFRFNhk5a/XImWm8a3urB1hUEPz66tsX1IAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T00:48:55.720288Z"},"content_sha256":"5524790b14c51b0ced0947f226fdc9be87bf4c3283f400f4db962199ee51a8e3","schema_version":"1.0","event_id":"sha256:5524790b14c51b0ced0947f226fdc9be87bf4c3283f400f4db962199ee51a8e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/bundle.json","state_url":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/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":"2026-06-06T00:48:55Z","links":{"resolver":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM","bundle":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/bundle.json","state":"https://pith.science/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDNE3EFGKNIC3ZZBDTUQWVXCKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TDNE3EFGKNIC3ZZBDTUQWVXCKM","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":"188a8f91e642b294904afebee2b67ee534ccb33e2099f75fe100c83ec5ac47d1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-10-01T23:39:25Z","title_canon_sha256":"8a7823b077ca7428fb14502354011970338828ca7a3c7301ff7edac22a4504e6"},"schema_version":"1.0","source":{"id":"1810.01014","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01014","created_at":"2026-05-17T23:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01014v2","created_at":"2026-05-17T23:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01014","created_at":"2026-05-17T23:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"TDNE3EFGKNIC","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TDNE3EFGKNIC3ZZB","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TDNE3EFG","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:5524790b14c51b0ced0947f226fdc9be87bf4c3283f400f4db962199ee51a8e3","target":"graph","created_at":"2026-05-17T23:46:46Z","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":"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","authors_text":"Aditya Mandalika, Brian Hou, Gilwoo Lee, Jeongseok Lee, Sanjiban Choudhury, Siddhartha S. Srinivasa","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-10-01T23:39:25Z","title":"Bayesian Policy Optimization for Model Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01014","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":"sha256:75e7263d402c1a734c0d1307eb5c6fa5e4d90d129a2cb33495aa05e4d60aaa78","target":"record","created_at":"2026-05-17T23:46:46Z","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":"188a8f91e642b294904afebee2b67ee534ccb33e2099f75fe100c83ec5ac47d1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-10-01T23:39:25Z","title_canon_sha256":"8a7823b077ca7428fb14502354011970338828ca7a3c7301ff7edac22a4504e6"},"schema_version":"1.0","source":{"id":"1810.01014","kind":"arxiv","version":2}},"canonical_sha256":"98da4d90a653502de7211ce90b56e2532adf5d9a49572c54167b0e8ce84554de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98da4d90a653502de7211ce90b56e2532adf5d9a49572c54167b0e8ce84554de","first_computed_at":"2026-05-17T23:46:46.089191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:46.089191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3dxQ4aRSSwzRhAMowV07cZ9KI4bsLhj4GQeNhYRW+waQOul697lc5rZ8ttfpWxPf5jPk5gSFRviynjGn/XQoBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:46.089714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.01014","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75e7263d402c1a734c0d1307eb5c6fa5e4d90d129a2cb33495aa05e4d60aaa78","sha256:5524790b14c51b0ced0947f226fdc9be87bf4c3283f400f4db962199ee51a8e3"],"state_sha256":"c9a64bcfd82a1fb86f5fe5685cbd535f8b7e5e3857836a16c04aa25ad13fc01f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TAxFXaJGjvZYtEShbcEe33SFmZZ1BH32HvElO8PqzTu+5kL9WlQ/NAbmYxAU09yaFhDJibI8enLr5nBWFZ3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T00:48:55.723408Z","bundle_sha256":"bb4b0f65de548bfe45fa95306fdda78c93b9a4cbebb6d1847dc434ee3b32ecc1"}}