{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3MXK3VYAIGKMFQXC6DOD4YCMJ4","short_pith_number":"pith:3MXK3VYA","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"},"canonical_sha256":"db2eadd7004194c2c2e2f0dc3e604c4f303236dd6b03f8e720fff58e75024cdb","source":{"kind":"arxiv","id":"2211.17116","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.17116","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2211.17116v1","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.17116","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"3MXK3VYAIGKM","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"3MXK3VYAIGKMFQXC","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"3MXK3VYA","created_at":"2026-07-05T05:21:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3MXK3VYAIGKMFQXC6DOD4YCMJ4","target":"record","payload":{"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"},"canonical_sha256":"db2eadd7004194c2c2e2f0dc3e604c4f303236dd6b03f8e720fff58e75024cdb","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"},"source_kind":"arxiv","source_id":"2211.17116","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pZ+sRBU/KkvDk5+19XwTZub6XA5G1RDS6eh3/8JS5/D+kpfWGIY7npTU2oxIw4sak5y5GesHDUoii70MNFpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:44:53.570136Z"},"content_sha256":"ac6dd3d5747376cf70259120ab6e83618795cd9bfdbbf4239b99bff2a45f591e","schema_version":"1.0","event_id":"sha256:ac6dd3d5747376cf70259120ab6e83618795cd9bfdbbf4239b99bff2a45f591e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3MXK3VYAIGKMFQXC6DOD4YCMJ4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yVJ6kzQdINxZKnThHMoN1442BM6XAAAGxNWV6mIlIU/NCMd3FbGC1U+GqXJnwYFEcKTYDYHYg65hIBrQma9gDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:44:53.570777Z"},"content_sha256":"255d8e81fbf9c9fe4b973680122df02597ea1e02c0a1a6cf11d28153d82d8c8e","schema_version":"1.0","event_id":"sha256:255d8e81fbf9c9fe4b973680122df02597ea1e02c0a1a6cf11d28153d82d8c8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/bundle.json","state_url":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T00:44:53Z","links":{"resolver":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4","bundle":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/bundle.json","state":"https://pith.science/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MXK3VYAIGKMFQXC6DOD4YCMJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3MXK3VYAIGKMFQXC6DOD4YCMJ4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"11499fb43ebb76eacc09536f133f13ad6f98401d69635a97635d34f3018a0b36","cross_cats_sorted":["cs.AI","cs.MA","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T15:58:00Z","title_canon_sha256":"7316b3e273b61e9811fec387672e63d3f7876d73db7bb719990bc5cf05a1d26a"},"schema_version":"1.0","source":{"id":"2211.17116","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.17116","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2211.17116v1","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.17116","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"3MXK3VYAIGKM","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"3MXK3VYAIGKMFQXC","created_at":"2026-07-05T05:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"3MXK3VYA","created_at":"2026-07-05T05:21:15Z"}],"graph_snapshots":[{"event_id":"sha256:255d8e81fbf9c9fe4b973680122df02597ea1e02c0a1a6cf11d28153d82d8c8e","target":"graph","created_at":"2026-07-05T05:21:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.17116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Adam Wierman, Guannan Qu, Pan Xu, Yiheng Lin, Yizhou Zhang, Zaiwei Chen","cross_cats":["cs.AI","cs.MA","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T15:58:00Z","title":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.17116","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac6dd3d5747376cf70259120ab6e83618795cd9bfdbbf4239b99bff2a45f591e","target":"record","created_at":"2026-07-05T05:21:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"11499fb43ebb76eacc09536f133f13ad6f98401d69635a97635d34f3018a0b36","cross_cats_sorted":["cs.AI","cs.MA","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T15:58:00Z","title_canon_sha256":"7316b3e273b61e9811fec387672e63d3f7876d73db7bb719990bc5cf05a1d26a"},"schema_version":"1.0","source":{"id":"2211.17116","kind":"arxiv","version":1}},"canonical_sha256":"db2eadd7004194c2c2e2f0dc3e604c4f303236dd6b03f8e720fff58e75024cdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db2eadd7004194c2c2e2f0dc3e604c4f303236dd6b03f8e720fff58e75024cdb","first_computed_at":"2026-07-05T05:21:15.296030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:15.296030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lnawu3HLxYv3nhmEmgZP7WUwHyrF5yWcU6nm2GVg5/KxkPOct/jrcLH8mj2NQqX4dA8eC3H/vL0zEv31z3g0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:15.296626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.17116","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac6dd3d5747376cf70259120ab6e83618795cd9bfdbbf4239b99bff2a45f591e","sha256:255d8e81fbf9c9fe4b973680122df02597ea1e02c0a1a6cf11d28153d82d8c8e"],"state_sha256":"d81893764b64c3fbe50ae7186bc11e1c057101d93e40cba43ad2cdc704173b6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9lNZpDenX1eXjhZVdquScs5J+NAsPpNdU0Kmlv9wrg9Z+mgO0mybqEzMwI/wjKHO4D9NWqnIezx7okf/1K33AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:44:53.576428Z","bundle_sha256":"b38c34997b05c701b8379315456bd9ff61c33d922fd941569c487e50bba1bafd"}}