{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:A4XKEHBQNUYDUTSEJ2SRAT2EL7","short_pith_number":"pith:A4XKEHBQ","schema_version":"1.0","canonical_sha256":"072ea21c306d303a4e444ea5104f445fddedef0f0964a4fa9793329fdd41ae84","source":{"kind":"arxiv","id":"2010.03599","version":1},"attestation_state":"computed","paper":{"title":"Improved POMDP Tree Search Planning with Prioritized Action Branching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anil Yildiz, John Mern, Larry Bush, Mykel J. Kochenderfer, Tapan Mukerji","submitted_at":"2020-10-07T18:33:57Z","abstract_excerpt":"Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. This paper proposes a method called PA-POMCPOW to sample a subset of the action space that provides varying mixtures of exploitation and exploration for inclusion in a search tree. The proposed method first evaluates the action space according to a score function that is a linear combination of expected reward and expected information gain. The actions with the highest score are then added to the search tree during tree expansion. Experiments show that PA-POMCPOW is a"},"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":"2010.03599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T18:33:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"599373dbc2ef203e1ad9f8ac5196f2382a9d3b6b4cdf7caa3b706ebb1e7a72df","abstract_canon_sha256":"c9232e7af06d3e43c3e0cb37aea47b5a86205aa9a5822de7669be6a2b4a7d8e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:35.280086Z","signature_b64":"4QsP0u0ELRTrYy2Mp13u1o4VR73GVMyNHNnVqpSZmhdxAnlxm3hNZvlbkqEoSKkjv09SMQGeQEmKY4DLB1WxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"072ea21c306d303a4e444ea5104f445fddedef0f0964a4fa9793329fdd41ae84","last_reissued_at":"2026-07-05T03:28:35.279573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:35.279573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved POMDP Tree Search Planning with Prioritized Action Branching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anil Yildiz, John Mern, Larry Bush, Mykel J. Kochenderfer, Tapan Mukerji","submitted_at":"2020-10-07T18:33:57Z","abstract_excerpt":"Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. This paper proposes a method called PA-POMCPOW to sample a subset of the action space that provides varying mixtures of exploitation and exploration for inclusion in a search tree. The proposed method first evaluates the action space according to a score function that is a linear combination of expected reward and expected information gain. The actions with the highest score are then added to the search tree during tree expansion. Experiments show that PA-POMCPOW is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03599","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.03599/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2010.03599","created_at":"2026-07-05T03:28:35.279638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03599v1","created_at":"2026-07-05T03:28:35.279638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03599","created_at":"2026-07-05T03:28:35.279638+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4XKEHBQNUYD","created_at":"2026-07-05T03:28:35.279638+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4XKEHBQNUYDUTSE","created_at":"2026-07-05T03:28:35.279638+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4XKEHBQ","created_at":"2026-07-05T03:28:35.279638+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/A4XKEHBQNUYDUTSEJ2SRAT2EL7","json":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7.json","graph_json":"https://pith.science/api/pith-number/A4XKEHBQNUYDUTSEJ2SRAT2EL7/graph.json","events_json":"https://pith.science/api/pith-number/A4XKEHBQNUYDUTSEJ2SRAT2EL7/events.json","paper":"https://pith.science/paper/A4XKEHBQ"},"agent_actions":{"view_html":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7","download_json":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7.json","view_paper":"https://pith.science/paper/A4XKEHBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03599&json=true","fetch_graph":"https://pith.science/api/pith-number/A4XKEHBQNUYDUTSEJ2SRAT2EL7/graph.json","fetch_events":"https://pith.science/api/pith-number/A4XKEHBQNUYDUTSEJ2SRAT2EL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7/action/storage_attestation","attest_author":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7/action/author_attestation","sign_citation":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7/action/citation_signature","submit_replication":"https://pith.science/pith/A4XKEHBQNUYDUTSEJ2SRAT2EL7/action/replication_record"}},"created_at":"2026-07-05T03:28:35.279638+00:00","updated_at":"2026-07-05T03:28:35.279638+00:00"}