{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:Y4TIOMF277FXMXAY73E5ZRV7U5","short_pith_number":"pith:Y4TIOMF2","schema_version":"1.0","canonical_sha256":"c7268730baffcb765c18fec9dcc6bfa771779f3d8e027538aecf662e74e05a0c","source":{"kind":"arxiv","id":"1401.3460","version":1},"attestation_state":"computed","paper":{"title":"Policy Iteration for Decentralized Control of Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Daniel S. Bernstein, Eric A. Hansen, Shlomo Zilberstein","submitted_at":"2014-01-15T05:20:25Z","abstract_excerpt":"Coordination of distributed agents is required for problems arising in many areas, including multi-robot systems, networking and e-commerce.  As a formal framework for such problems, we use the decentralized partially observable Markov decision process (DEC-POMDP).  Though much work has been done on optimal dynamic programming algorithms for the single-agent version of the problem, optimal algorithms for the multiagent case have been elusive.  The main contribution of this paper is an optimal policy iteration algorithm for solving DEC-POMDPs.  The algorithm uses stochastic finite-state control"},"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":"1401.3460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-01-15T05:20:25Z","cross_cats_sorted":[],"title_canon_sha256":"9d4e783eae79c36a3d9715128a0eace502db009a8e58d9c128410e0ebdee6755","abstract_canon_sha256":"50c588ea38491838b273eaa01ba004494d85efc5048985c73c0dcaa1588cc022"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:02:08.962974Z","signature_b64":"mta+qAEkJA7pDM3ImPUXDRiyY6Aysw35ftbssJP+Auz2sFrsK63Gt5poDxSYhL4GQ0nKvHBT1T4fPDDbqjfnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7268730baffcb765c18fec9dcc6bfa771779f3d8e027538aecf662e74e05a0c","last_reissued_at":"2026-05-18T03:02:08.962287Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:02:08.962287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Iteration for Decentralized Control of Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Daniel S. Bernstein, Eric A. Hansen, Shlomo Zilberstein","submitted_at":"2014-01-15T05:20:25Z","abstract_excerpt":"Coordination of distributed agents is required for problems arising in many areas, including multi-robot systems, networking and e-commerce.  As a formal framework for such problems, we use the decentralized partially observable Markov decision process (DEC-POMDP).  Though much work has been done on optimal dynamic programming algorithms for the single-agent version of the problem, optimal algorithms for the multiagent case have been elusive.  The main contribution of this paper is an optimal policy iteration algorithm for solving DEC-POMDPs.  The algorithm uses stochastic finite-state control"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.3460","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":"1401.3460","created_at":"2026-05-18T03:02:08.962434+00:00"},{"alias_kind":"arxiv_version","alias_value":"1401.3460v1","created_at":"2026-05-18T03:02:08.962434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.3460","created_at":"2026-05-18T03:02:08.962434+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4TIOMF277FX","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4TIOMF277FXMXAY","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4TIOMF2","created_at":"2026-05-18T12:28:57.508820+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/Y4TIOMF277FXMXAY73E5ZRV7U5","json":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5.json","graph_json":"https://pith.science/api/pith-number/Y4TIOMF277FXMXAY73E5ZRV7U5/graph.json","events_json":"https://pith.science/api/pith-number/Y4TIOMF277FXMXAY73E5ZRV7U5/events.json","paper":"https://pith.science/paper/Y4TIOMF2"},"agent_actions":{"view_html":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5","download_json":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5.json","view_paper":"https://pith.science/paper/Y4TIOMF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1401.3460&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4TIOMF277FXMXAY73E5ZRV7U5/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4TIOMF277FXMXAY73E5ZRV7U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5/action/storage_attestation","attest_author":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5/action/author_attestation","sign_citation":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5/action/citation_signature","submit_replication":"https://pith.science/pith/Y4TIOMF277FXMXAY73E5ZRV7U5/action/replication_record"}},"created_at":"2026-05-18T03:02:08.962434+00:00","updated_at":"2026-05-18T03:02:08.962434+00:00"}