{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HJ4JLDJMZH3742IXZFKTR6HQKE","short_pith_number":"pith:HJ4JLDJM","canonical_record":{"source":{"id":"2006.06626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-11T17:23:17Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"418646c39ad462a22428743708828bb10fa6cc826d7b601361e5ef5a0455e680","abstract_canon_sha256":"46d89a75d951f23357ba3573da9e5680968960c60afc404cee2095fd1ff22477"},"schema_version":"1.0"},"canonical_sha256":"3a78958d2cc9f7fe6917c95538f8f0513d4f8085e2b18a713e6b6f05413a23aa","source":{"kind":"arxiv","id":"2006.06626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06626","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06626v1","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06626","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"HJ4JLDJMZH37","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"pith_short_16","alias_value":"HJ4JLDJMZH3742IX","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"pith_short_8","alias_value":"HJ4JLDJM","created_at":"2026-07-05T01:09:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HJ4JLDJMZH3742IXZFKTR6HQKE","target":"record","payload":{"canonical_record":{"source":{"id":"2006.06626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-11T17:23:17Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"418646c39ad462a22428743708828bb10fa6cc826d7b601361e5ef5a0455e680","abstract_canon_sha256":"46d89a75d951f23357ba3573da9e5680968960c60afc404cee2095fd1ff22477"},"schema_version":"1.0"},"canonical_sha256":"3a78958d2cc9f7fe6917c95538f8f0513d4f8085e2b18a713e6b6f05413a23aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:35.159362Z","signature_b64":"/rU7wXKUZjnJm4ayd3Sl2llAbEyESUP2lAc0JToS/zcWnjKcPQxit3fALJIlUPT0d7gijH3lP7dq7eMhO1rOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a78958d2cc9f7fe6917c95538f8f0513d4f8085e2b18a713e6b6f05413a23aa","last_reissued_at":"2026-07-05T01:09:35.158947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:35.158947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.06626","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":"2026-07-05T01:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zCN2qmxzM9KHJlpRoRwAvtfgX2hvAQ0ljfWVtVKIbpu1aFgCUupY8/PCJbjXDZ2cxBGdX0phL6+Pi+Pmo1LtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:22:00.511052Z"},"content_sha256":"4b71be3baee8ebe45a41bc454b114ba287103ee5abe03d29ce4e37f401e7eb82","schema_version":"1.0","event_id":"sha256:4b71be3baee8ebe45a41bc454b114ba287103ee5abe03d29ce4e37f401e7eb82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HJ4JLDJMZH3742IXZFKTR6HQKE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Adam Wierman, Guannan Qu, Na Li, Yiheng Lin","submitted_at":"2020-06-11T17:23:17Z","abstract_excerpt":"It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we identify a rich class of networked MARL problems where the model exhibits a local dependence structure that allows it to be solved in a scalable manner. Specifically, we propose a Scalable Actor-Critic (SAC) method that can learn a near optimal localized policy for optimizing the average reward with complexity scaling with the state-action space size of loca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06626","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/2006.06626/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":"2026-07-05T01:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EmaiSb3JgSpk99zcGLJy+mznVio8GYirj4ZVSK2ZxEWAfs9CMK26Q5n0MoNLRiG7XcFN3W4XH5OZlmNQJyF/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:22:00.511991Z"},"content_sha256":"d189ae5f08a8ef447aef6a6f0f9b78f50d6a2c3f5833cd3772f612d6b1576e81","schema_version":"1.0","event_id":"sha256:d189ae5f08a8ef447aef6a6f0f9b78f50d6a2c3f5833cd3772f612d6b1576e81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJ4JLDJMZH3742IXZFKTR6HQKE/bundle.json","state_url":"https://pith.science/pith/HJ4JLDJMZH3742IXZFKTR6HQKE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJ4JLDJMZH3742IXZFKTR6HQKE/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":"2026-08-17T20:22:00Z","links":{"resolver":"https://pith.science/pith/HJ4JLDJMZH3742IXZFKTR6HQKE","bundle":"https://pith.science/pith/HJ4JLDJMZH3742IXZFKTR6HQKE/bundle.json","state":"https://pith.science/pith/HJ4JLDJMZH3742IXZFKTR6HQKE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJ4JLDJMZH3742IXZFKTR6HQKE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HJ4JLDJMZH3742IXZFKTR6HQKE","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":"46d89a75d951f23357ba3573da9e5680968960c60afc404cee2095fd1ff22477","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-11T17:23:17Z","title_canon_sha256":"418646c39ad462a22428743708828bb10fa6cc826d7b601361e5ef5a0455e680"},"schema_version":"1.0","source":{"id":"2006.06626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06626","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06626v1","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06626","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"HJ4JLDJMZH37","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"pith_short_16","alias_value":"HJ4JLDJMZH3742IX","created_at":"2026-07-05T01:09:35Z"},{"alias_kind":"pith_short_8","alias_value":"HJ4JLDJM","created_at":"2026-07-05T01:09:35Z"}],"graph_snapshots":[{"event_id":"sha256:d189ae5f08a8ef447aef6a6f0f9b78f50d6a2c3f5833cd3772f612d6b1576e81","target":"graph","created_at":"2026-07-05T01:09:35Z","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/2006.06626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we identify a rich class of networked MARL problems where the model exhibits a local dependence structure that allows it to be solved in a scalable manner. Specifically, we propose a Scalable Actor-Critic (SAC) method that can learn a near optimal localized policy for optimizing the average reward with complexity scaling with the state-action space size of loca","authors_text":"Adam Wierman, Guannan Qu, Na Li, Yiheng Lin","cross_cats":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-11T17:23:17Z","title":"Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06626","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":"sha256:4b71be3baee8ebe45a41bc454b114ba287103ee5abe03d29ce4e37f401e7eb82","target":"record","created_at":"2026-07-05T01:09:35Z","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":"46d89a75d951f23357ba3573da9e5680968960c60afc404cee2095fd1ff22477","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-11T17:23:17Z","title_canon_sha256":"418646c39ad462a22428743708828bb10fa6cc826d7b601361e5ef5a0455e680"},"schema_version":"1.0","source":{"id":"2006.06626","kind":"arxiv","version":1}},"canonical_sha256":"3a78958d2cc9f7fe6917c95538f8f0513d4f8085e2b18a713e6b6f05413a23aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a78958d2cc9f7fe6917c95538f8f0513d4f8085e2b18a713e6b6f05413a23aa","first_computed_at":"2026-07-05T01:09:35.158947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:35.158947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/rU7wXKUZjnJm4ayd3Sl2llAbEyESUP2lAc0JToS/zcWnjKcPQxit3fALJIlUPT0d7gijH3lP7dq7eMhO1rOAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:35.159362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b71be3baee8ebe45a41bc454b114ba287103ee5abe03d29ce4e37f401e7eb82","sha256:d189ae5f08a8ef447aef6a6f0f9b78f50d6a2c3f5833cd3772f612d6b1576e81"],"state_sha256":"c6474467160a3b7c7945c236b9a8a92ce4450fee98b45dda944756203d51f7ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GhjwQp4XxrYx9I45dGJaysR73bd2PbnqOKNKcM4ErQNbWIMWbBYyvBCSRWriLEKNYMlFcsMkoJS44EnlHX2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:22:00.600723Z","bundle_sha256":"5fe3d847cff1ff81cd3b5ded89cdf78a1bc424ab6269eaa22676eb10d4f47d4a"}}