{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3MXK3VYAIGKMFQXC6DOD4YCMJ4","short_pith_number":"pith:3MXK3VYA","schema_version":"1.0","canonical_sha256":"db2eadd7004194c2c2e2f0dc3e604c4f303236dd6b03f8e720fff58e75024cdb","source":{"kind":"arxiv","id":"2211.17116","version":1},"attestation_state":"computed","paper":{"title":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","math.OC"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Guannan Qu, Pan Xu, Yiheng Lin, Yizhou Zhang, Zaiwei Chen","submitted_at":"2022-11-30T15:58:00Z","abstract_excerpt":"We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the curse of dimensionality and to reduce communication, we propose a Localized Policy Iteration (LPI) algorithm that provably learns a near-globally-optimal policy using only local information. In particular, we show that, despite restricting each agent's attention to only its $\\kappa$-hop neighborhood, the agents are able to learn a policy with an optimality gap "},"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":"2211.17116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T15:58:00Z","cross_cats_sorted":["cs.AI","cs.MA","math.OC"],"title_canon_sha256":"7316b3e273b61e9811fec387672e63d3f7876d73db7bb719990bc5cf05a1d26a","abstract_canon_sha256":"11499fb43ebb76eacc09536f133f13ad6f98401d69635a97635d34f3018a0b36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:15.296626Z","signature_b64":"Lnawu3HLxYv3nhmEmgZP7WUwHyrF5yWcU6nm2GVg5/KxkPOct/jrcLH8mj2NQqX4dA8eC3H/vL0zEv31z3g0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db2eadd7004194c2c2e2f0dc3e604c4f303236dd6b03f8e720fff58e75024cdb","last_reissued_at":"2026-07-05T05:21:15.296030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:15.296030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","math.OC"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Guannan Qu, Pan Xu, Yiheng Lin, Yizhou Zhang, Zaiwei Chen","submitted_at":"2022-11-30T15:58:00Z","abstract_excerpt":"We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the curse of dimensionality and to reduce communication, we propose a Localized Policy Iteration (LPI) algorithm that provably learns a near-globally-optimal policy using only local information. In particular, we show that, despite restricting each agent's attention to only its $\\kappa$-hop neighborhood, the agents are able to learn a policy with an optimality gap "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.17116","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/2211.17116/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":"2211.17116","created_at":"2026-07-05T05:21:15.296092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.17116v1","created_at":"2026-07-05T05:21:15.296092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.17116","created_at":"2026-07-05T05:21:15.296092+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MXK3VYAIGKM","created_at":"2026-07-05T05:21:15.296092+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MXK3VYAIGKMFQXC","created_at":"2026-07-05T05:21:15.296092+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MXK3VYA","created_at":"2026-07-05T05:21:15.296092+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/3MXK3VYAIGKMFQXC6DOD4YCMJ4","json":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4.json","graph_json":"https://pith.science/api/pith-number/3MXK3VYAIGKMFQXC6DOD4YCMJ4/graph.json","events_json":"https://pith.science/api/pith-number/3MXK3VYAIGKMFQXC6DOD4YCMJ4/events.json","paper":"https://pith.science/paper/3MXK3VYA"},"agent_actions":{"view_html":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4","download_json":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4.json","view_paper":"https://pith.science/paper/3MXK3VYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.17116&json=true","fetch_graph":"https://pith.science/api/pith-number/3MXK3VYAIGKMFQXC6DOD4YCMJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/3MXK3VYAIGKMFQXC6DOD4YCMJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/action/storage_attestation","attest_author":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/action/author_attestation","sign_citation":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/action/citation_signature","submit_replication":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/action/replication_record"}},"created_at":"2026-07-05T05:21:15.296092+00:00","updated_at":"2026-07-05T05:21:15.296092+00:00"}