{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VVZU2FOO63F4MWBSEO5TFA227E","short_pith_number":"pith:VVZU2FOO","canonical_record":{"source":{"id":"2108.08612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T10:49:10Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"b4ba0e844243c403f9062c1c8cf3d867ff36560d0f7c0357a00c800b46c40332","abstract_canon_sha256":"5409ef80ebdd37259991c0bd82d9272e1cb000d245818acf23cdcbd3243eca9a"},"schema_version":"1.0"},"canonical_sha256":"ad734d15cef6cbc6583223bb32835af903cca97deb284b8fee94c1004b52e959","source":{"kind":"arxiv","id":"2108.08612","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08612","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08612v3","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08612","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"VVZU2FOO63F4","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"VVZU2FOO63F4MWBS","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"VVZU2FOO","created_at":"2026-07-05T04:11:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VVZU2FOO63F4MWBSEO5TFA227E","target":"record","payload":{"canonical_record":{"source":{"id":"2108.08612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T10:49:10Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"b4ba0e844243c403f9062c1c8cf3d867ff36560d0f7c0357a00c800b46c40332","abstract_canon_sha256":"5409ef80ebdd37259991c0bd82d9272e1cb000d245818acf23cdcbd3243eca9a"},"schema_version":"1.0"},"canonical_sha256":"ad734d15cef6cbc6583223bb32835af903cca97deb284b8fee94c1004b52e959","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:07.071927Z","signature_b64":"fzL5FmUsvd6iqol+j84jn9JdieFZ6klHIyaIZrU41oWV5S+k3ewNQOEWVMpKlGOi4GKKSmHTiX9i4qdcpej1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad734d15cef6cbc6583223bb32835af903cca97deb284b8fee94c1004b52e959","last_reissued_at":"2026-07-05T04:11:07.071362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:07.071362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.08612","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LdCp5bWe3WOhPlGTyOefw0qAlgOp6pOt7jezIh0k47G5MMtUyAn9Nh5ntOd98EIADLKA8C/E5o0Uod9JCPjPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:41:32.559043Z"},"content_sha256":"de3d1face8f9752db7d4344931b89dbe5594edbd220fdf97ea7ac00eae7779ba","schema_version":"1.0","event_id":"sha256:de3d1face8f9752db7d4344931b89dbe5594edbd220fdf97ea7ac00eae7779ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VVZU2FOO63F4MWBSEO5TFA227E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Settling the Variance of Multi-Agent Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"David Henry Mguni, Haifeng Zhang, Jakub Grudzien Kuba, Jun Wang, Linghui Meng, Muning Wen, Shangding Gu, Yaodong Yang","submitted_at":"2021-08-19T10:49:10Z","abstract_excerpt":"Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL (MARL), although the PG theorem can be naturally extended, the effectiveness of multi-agent PG (MAPG) methods degrades as the variance of gradient estimates increases rapidly with the number of agents. In this paper, we offer a rigorous analysis of MAPG methods by, firstly, quantifying the contributions of the number of agents and agents' explorations to the variance of MAPG estimators. Based on this analysis, we derive t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08612","kind":"arxiv","version":3},"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/2108.08612/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":"2026-07-05T04:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuqLIvztjIGq6OwX9OgLPgZrn1KySpU42J67bKftst1OvAvnsY4dJpc45I2bOHZpU9D04I2KPeusqY3Wddt5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:41:32.559672Z"},"content_sha256":"3ff0400ce0832d44eefec1573c5bd321b474aaf68c4805f41471630ec622faab","schema_version":"1.0","event_id":"sha256:3ff0400ce0832d44eefec1573c5bd321b474aaf68c4805f41471630ec622faab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVZU2FOO63F4MWBSEO5TFA227E/bundle.json","state_url":"https://pith.science/pith/VVZU2FOO63F4MWBSEO5TFA227E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVZU2FOO63F4MWBSEO5TFA227E/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":"2026-07-05T14:41:32Z","links":{"resolver":"https://pith.science/pith/VVZU2FOO63F4MWBSEO5TFA227E","bundle":"https://pith.science/pith/VVZU2FOO63F4MWBSEO5TFA227E/bundle.json","state":"https://pith.science/pith/VVZU2FOO63F4MWBSEO5TFA227E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVZU2FOO63F4MWBSEO5TFA227E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VVZU2FOO63F4MWBSEO5TFA227E","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":"5409ef80ebdd37259991c0bd82d9272e1cb000d245818acf23cdcbd3243eca9a","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T10:49:10Z","title_canon_sha256":"b4ba0e844243c403f9062c1c8cf3d867ff36560d0f7c0357a00c800b46c40332"},"schema_version":"1.0","source":{"id":"2108.08612","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08612","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08612v3","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08612","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"VVZU2FOO63F4","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"VVZU2FOO63F4MWBS","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"VVZU2FOO","created_at":"2026-07-05T04:11:07Z"}],"graph_snapshots":[{"event_id":"sha256:3ff0400ce0832d44eefec1573c5bd321b474aaf68c4805f41471630ec622faab","target":"graph","created_at":"2026-07-05T04:11:07Z","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/2108.08612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL (MARL), although the PG theorem can be naturally extended, the effectiveness of multi-agent PG (MAPG) methods degrades as the variance of gradient estimates increases rapidly with the number of agents. In this paper, we offer a rigorous analysis of MAPG methods by, firstly, quantifying the contributions of the number of agents and agents' explorations to the variance of MAPG estimators. Based on this analysis, we derive t","authors_text":"David Henry Mguni, Haifeng Zhang, Jakub Grudzien Kuba, Jun Wang, Linghui Meng, Muning Wen, Shangding Gu, Yaodong Yang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T10:49:10Z","title":"Settling the Variance of Multi-Agent Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08612","kind":"arxiv","version":3},"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:de3d1face8f9752db7d4344931b89dbe5594edbd220fdf97ea7ac00eae7779ba","target":"record","created_at":"2026-07-05T04:11:07Z","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":"5409ef80ebdd37259991c0bd82d9272e1cb000d245818acf23cdcbd3243eca9a","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T10:49:10Z","title_canon_sha256":"b4ba0e844243c403f9062c1c8cf3d867ff36560d0f7c0357a00c800b46c40332"},"schema_version":"1.0","source":{"id":"2108.08612","kind":"arxiv","version":3}},"canonical_sha256":"ad734d15cef6cbc6583223bb32835af903cca97deb284b8fee94c1004b52e959","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad734d15cef6cbc6583223bb32835af903cca97deb284b8fee94c1004b52e959","first_computed_at":"2026-07-05T04:11:07.071362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:07.071362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fzL5FmUsvd6iqol+j84jn9JdieFZ6klHIyaIZrU41oWV5S+k3ewNQOEWVMpKlGOi4GKKSmHTiX9i4qdcpej1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:07.071927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.08612","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de3d1face8f9752db7d4344931b89dbe5594edbd220fdf97ea7ac00eae7779ba","sha256:3ff0400ce0832d44eefec1573c5bd321b474aaf68c4805f41471630ec622faab"],"state_sha256":"1ffded1616f3c6cf41a56586ba0a29da2a3947dc92b3180dd4bdad0106d7dff5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59tEIhYM5JcVauV8lypcCjgKq/B/aJUrsiuNJ3LJEtZdEHQcDUlIKzxWfJD54GC33FQBXQxkI9o98cGP79qCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:41:32.563168Z","bundle_sha256":"59cb8aef489c59bb69482a161e806a0ca05a43c246816107497a050975c43f74"}}