{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NNOR6N4FLJXSAWCL2WLGACZTNM","short_pith_number":"pith:NNOR6N4F","schema_version":"1.0","canonical_sha256":"6b5d1f37855a6f20584bd596600b336b0fd94d77e67734af11f372538ef5d169","source":{"kind":"arxiv","id":"1806.05631","version":1},"attestation_state":"computed","paper":{"title":"Learning in POMDPs with Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Frans A. Oliehoek, Sammie Katt","submitted_at":"2018-06-14T16:17:44Z","abstract_excerpt":"The POMDP is a powerful framework for reasoning under outcome and information uncertainty, but constructing an accurate POMDP model is difficult. Bayes-Adaptive Partially Observable Markov Decision Processes (BA-POMDPs) extend POMDPs to allow the model to be learned during execution. BA-POMDPs are a Bayesian RL approach that, in principle, allows for an optimal trade-off between exploitation and exploration. Unfortunately, BA-POMDPs are currently impractical to solve for any non-trivial domain. In this paper, we extend the Monte-Carlo Tree Search method POMCP to BA-POMDPs and show that the res"},"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":"1806.05631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T16:17:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3010a3978e31669389274c1964efe86a097b3b4a6834cd25ab10c3a4df8833a7","abstract_canon_sha256":"30f24a5da4222a60ceac8868eb8f4ec3fc264c04fec890124f52f5cdcda4a1a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:14.554080Z","signature_b64":"PDB9KHeqLnQ8Yp+44h1nZiWc2ZPlhNG4HBrU12/tC6V7+BHSu7YInZj6ZM9k2+YmAxTD7MG/tj9JRyfOKfVsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b5d1f37855a6f20584bd596600b336b0fd94d77e67734af11f372538ef5d169","last_reissued_at":"2026-05-18T00:13:14.553395Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:14.553395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning in POMDPs with Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Frans A. Oliehoek, Sammie Katt","submitted_at":"2018-06-14T16:17:44Z","abstract_excerpt":"The POMDP is a powerful framework for reasoning under outcome and information uncertainty, but constructing an accurate POMDP model is difficult. Bayes-Adaptive Partially Observable Markov Decision Processes (BA-POMDPs) extend POMDPs to allow the model to be learned during execution. BA-POMDPs are a Bayesian RL approach that, in principle, allows for an optimal trade-off between exploitation and exploration. Unfortunately, BA-POMDPs are currently impractical to solve for any non-trivial domain. In this paper, we extend the Monte-Carlo Tree Search method POMCP to BA-POMDPs and show that the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05631","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":"1806.05631","created_at":"2026-05-18T00:13:14.553499+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05631v1","created_at":"2026-05-18T00:13:14.553499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05631","created_at":"2026-05-18T00:13:14.553499+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNOR6N4FLJXS","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNOR6N4FLJXSAWCL","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNOR6N4F","created_at":"2026-05-18T12:32:40.477152+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/NNOR6N4FLJXSAWCL2WLGACZTNM","json":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM.json","graph_json":"https://pith.science/api/pith-number/NNOR6N4FLJXSAWCL2WLGACZTNM/graph.json","events_json":"https://pith.science/api/pith-number/NNOR6N4FLJXSAWCL2WLGACZTNM/events.json","paper":"https://pith.science/paper/NNOR6N4F"},"agent_actions":{"view_html":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM","download_json":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM.json","view_paper":"https://pith.science/paper/NNOR6N4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05631&json=true","fetch_graph":"https://pith.science/api/pith-number/NNOR6N4FLJXSAWCL2WLGACZTNM/graph.json","fetch_events":"https://pith.science/api/pith-number/NNOR6N4FLJXSAWCL2WLGACZTNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/action/storage_attestation","attest_author":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/action/author_attestation","sign_citation":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/action/citation_signature","submit_replication":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/action/replication_record"}},"created_at":"2026-05-18T00:13:14.553499+00:00","updated_at":"2026-05-18T00:13:14.553499+00:00"}