{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:NSNLLGV3XDJBWAKEBU4EL6BEP2","short_pith_number":"pith:NSNLLGV3","schema_version":"1.0","canonical_sha256":"6c9ab59abbb8d21b01440d3845f8247e804abd1579ec6855e50379759a7969de","source":{"kind":"arxiv","id":"1312.7606","version":2},"attestation_state":"computed","paper":{"title":"Distributed Policy Evaluation Under Multiple Behavior Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG"],"primary_cat":"cs.MA","authors_text":"Ali H. Sayed, Jianshu Chen, Santiago Zazo, Sergio Valcarcel Macua","submitted_at":"2013-12-30T00:16:34Z","abstract_excerpt":"We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The algorithm can also be applied to off-policy learning, meaning that the agents can predict the response to a behavior different from the actual policies they are following. The proposed distributed strategy is efficient, with linear complexity in both computation time and memory footprint. We provide a mean-square-error performance analysis and establish convergen"},"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":"1312.7606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2013-12-30T00:16:34Z","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"title_canon_sha256":"28a9b533fd2d2b8ad6114d71e57c66f94d8973bb033a5754ee489d6da8b006f7","abstract_canon_sha256":"5c86991d6c27288234a3db8fcea0c98f9b9cb4220a5c8de53f1af82fe4867960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:37.290995Z","signature_b64":"KDf97/N/MiYbOWb+eyw5P+p6X91YI5XVckNwrfLXVC63Jk/FQnQgmd80ACKulyqdIKxrvcqTL+SB0X1LDkLRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c9ab59abbb8d21b01440d3845f8247e804abd1579ec6855e50379759a7969de","last_reissued_at":"2026-05-18T02:38:37.290475Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:37.290475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Policy Evaluation Under Multiple Behavior Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG"],"primary_cat":"cs.MA","authors_text":"Ali H. Sayed, Jianshu Chen, Santiago Zazo, Sergio Valcarcel Macua","submitted_at":"2013-12-30T00:16:34Z","abstract_excerpt":"We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The algorithm can also be applied to off-policy learning, meaning that the agents can predict the response to a behavior different from the actual policies they are following. The proposed distributed strategy is efficient, with linear complexity in both computation time and memory footprint. We provide a mean-square-error performance analysis and establish convergen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.7606","kind":"arxiv","version":2},"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":"1312.7606","created_at":"2026-05-18T02:38:37.290557+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.7606v2","created_at":"2026-05-18T02:38:37.290557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.7606","created_at":"2026-05-18T02:38:37.290557+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSNLLGV3XDJB","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSNLLGV3XDJBWAKE","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSNLLGV3","created_at":"2026-05-18T12:27:52.871228+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/NSNLLGV3XDJBWAKEBU4EL6BEP2","json":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2.json","graph_json":"https://pith.science/api/pith-number/NSNLLGV3XDJBWAKEBU4EL6BEP2/graph.json","events_json":"https://pith.science/api/pith-number/NSNLLGV3XDJBWAKEBU4EL6BEP2/events.json","paper":"https://pith.science/paper/NSNLLGV3"},"agent_actions":{"view_html":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2","download_json":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2.json","view_paper":"https://pith.science/paper/NSNLLGV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.7606&json=true","fetch_graph":"https://pith.science/api/pith-number/NSNLLGV3XDJBWAKEBU4EL6BEP2/graph.json","fetch_events":"https://pith.science/api/pith-number/NSNLLGV3XDJBWAKEBU4EL6BEP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2/action/storage_attestation","attest_author":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2/action/author_attestation","sign_citation":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2/action/citation_signature","submit_replication":"https://pith.science/pith/NSNLLGV3XDJBWAKEBU4EL6BEP2/action/replication_record"}},"created_at":"2026-05-18T02:38:37.290557+00:00","updated_at":"2026-05-18T02:38:37.290557+00:00"}