{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:NQAT3IEUE4ZQ2YKUB4IS3I2NCG","short_pith_number":"pith:NQAT3IEU","schema_version":"1.0","canonical_sha256":"6c013da09427330d61540f112da34d119dc4869e98a6c2ca395a29f06ed0dca2","source":{"kind":"arxiv","id":"1203.3528","version":1},"attestation_state":"computed","paper":{"title":"Rollout Sampling Policy Iteration for Decentralized POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feng Wu, Shlomo Zilberstein, Xiaoping Chen","submitted_at":"2012-03-15T11:17:56Z","abstract_excerpt":"We present decentralized rollout sampling policy iteration (DecRSPI) - a new algorithm for multi-agent decision problems formalized as DEC-POMDPs. DecRSPI is designed to improve scalability and tackle problems that lack an explicit model. The algorithm uses Monte- Carlo methods to generate a sample of reachable belief states. Then it computes a joint policy for each belief state based on the rollout estimations. A new policy representation allows us to represent solutions compactly. The key benefits of the algorithm are its linear time complexity over the number of agents, its bounded memory u"},"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":"1203.3528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-03-15T11:17:56Z","cross_cats_sorted":[],"title_canon_sha256":"98f4113d1f70908f3d08bf28b9563d3ac4d9fc42d0155057c1ac297cfc909e53","abstract_canon_sha256":"9046e7e8054eb65c8ef26a4ec733d95a8274c7e6b38413b19caceb4866fc6f8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:59:59.841055Z","signature_b64":"s4icT5J7KTRFQOGiZcEQ0gUlGk0UA/N8OWGIrdqRz60l+0AOPTTKn58n3DDpRtxstUV0O0XxSc6jnTXnlSPTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c013da09427330d61540f112da34d119dc4869e98a6c2ca395a29f06ed0dca2","last_reissued_at":"2026-05-18T03:59:59.840280Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:59:59.840280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rollout Sampling Policy Iteration for Decentralized POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feng Wu, Shlomo Zilberstein, Xiaoping Chen","submitted_at":"2012-03-15T11:17:56Z","abstract_excerpt":"We present decentralized rollout sampling policy iteration (DecRSPI) - a new algorithm for multi-agent decision problems formalized as DEC-POMDPs. DecRSPI is designed to improve scalability and tackle problems that lack an explicit model. The algorithm uses Monte- Carlo methods to generate a sample of reachable belief states. Then it computes a joint policy for each belief state based on the rollout estimations. A new policy representation allows us to represent solutions compactly. The key benefits of the algorithm are its linear time complexity over the number of agents, its bounded memory u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.3528","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":"1203.3528","created_at":"2026-05-18T03:59:59.840403+00:00"},{"alias_kind":"arxiv_version","alias_value":"1203.3528v1","created_at":"2026-05-18T03:59:59.840403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.3528","created_at":"2026-05-18T03:59:59.840403+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQAT3IEUE4ZQ","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQAT3IEUE4ZQ2YKU","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQAT3IEU","created_at":"2026-05-18T12:27:16.716162+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/NQAT3IEUE4ZQ2YKUB4IS3I2NCG","json":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG.json","graph_json":"https://pith.science/api/pith-number/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/graph.json","events_json":"https://pith.science/api/pith-number/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/events.json","paper":"https://pith.science/paper/NQAT3IEU"},"agent_actions":{"view_html":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG","download_json":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG.json","view_paper":"https://pith.science/paper/NQAT3IEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1203.3528&json=true","fetch_graph":"https://pith.science/api/pith-number/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/graph.json","fetch_events":"https://pith.science/api/pith-number/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/action/storage_attestation","attest_author":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/action/author_attestation","sign_citation":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/action/citation_signature","submit_replication":"https://pith.science/pith/NQAT3IEUE4ZQ2YKUB4IS3I2NCG/action/replication_record"}},"created_at":"2026-05-18T03:59:59.840403+00:00","updated_at":"2026-05-18T03:59:59.840403+00:00"}