{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UDZB46TMEOXHDVD47MKPGO2GN2","short_pith_number":"pith:UDZB46TM","schema_version":"1.0","canonical_sha256":"a0f21e7a6c23ae71d47cfb14f33b466e9503c5ea0a6580fcab13e5075ba90d9f","source":{"kind":"arxiv","id":"1811.05612","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Reinforcement Learning in Factored POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Frans Oliehoek, Sammie Katt","submitted_at":"2018-11-14T02:47:05Z","abstract_excerpt":"Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the Factored Bayes-Adaptive POMDP model, a framework that is able to exploit the underlying structure while learning the dynamics in partially observable systems. We also present a belief tracking method to approximate the joint posterior over state and model variables, and an adaptation of the Monte-Carlo Tree Search solution method, which together are capable of so"},"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":"1811.05612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-14T02:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"65f0cb4907b5b577ce8b5d38fa4556171d3c1896451a7dd9489fb18de3ca361a","abstract_canon_sha256":"048126a7a5dbcfb82c8c0e0d683db81e4d689dc65782324589a67fd9da0e4a17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:42.531051Z","signature_b64":"1YKDRddDhGWNU8VX6XCPxKCVJdTv5lPyQoeMMYgc9AeRI/Tvo2otYBU9ozw0Am1WGyNA0hZ1DN7KBWKhzyfxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f21e7a6c23ae71d47cfb14f33b466e9503c5ea0a6580fcab13e5075ba90d9f","last_reissued_at":"2026-05-18T00:00:42.530588Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:42.530588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Reinforcement Learning in Factored POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Frans Oliehoek, Sammie Katt","submitted_at":"2018-11-14T02:47:05Z","abstract_excerpt":"Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the Factored Bayes-Adaptive POMDP model, a framework that is able to exploit the underlying structure while learning the dynamics in partially observable systems. We also present a belief tracking method to approximate the joint posterior over state and model variables, and an adaptation of the Monte-Carlo Tree Search solution method, which together are capable of so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05612","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":"1811.05612","created_at":"2026-05-18T00:00:42.530661+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.05612v1","created_at":"2026-05-18T00:00:42.530661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05612","created_at":"2026-05-18T00:00:42.530661+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDZB46TMEOXH","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDZB46TMEOXHDVD4","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDZB46TM","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.04935","citing_title":"What Type of Inference is Active Inference?","ref_index":164,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20658","citing_title":"Expected Free Energy-based Planning as Variational Inference","ref_index":150,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2","json":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2.json","graph_json":"https://pith.science/api/pith-number/UDZB46TMEOXHDVD47MKPGO2GN2/graph.json","events_json":"https://pith.science/api/pith-number/UDZB46TMEOXHDVD47MKPGO2GN2/events.json","paper":"https://pith.science/paper/UDZB46TM"},"agent_actions":{"view_html":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2","download_json":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2.json","view_paper":"https://pith.science/paper/UDZB46TM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.05612&json=true","fetch_graph":"https://pith.science/api/pith-number/UDZB46TMEOXHDVD47MKPGO2GN2/graph.json","fetch_events":"https://pith.science/api/pith-number/UDZB46TMEOXHDVD47MKPGO2GN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/action/storage_attestation","attest_author":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/action/author_attestation","sign_citation":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/action/citation_signature","submit_replication":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/action/replication_record"}},"created_at":"2026-05-18T00:00:42.530661+00:00","updated_at":"2026-05-18T00:00:42.530661+00:00"}