{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PJCYEGIXQ4TSINKV42LY6GXVQQ","short_pith_number":"pith:PJCYEGIX","canonical_record":{"source":{"id":"2006.00587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-31T19:14:03Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"d64b054152f7f779f334325cc819edf1bd28de13c4c7db2e9517a3afca82e441","abstract_canon_sha256":"8f8cc08b519f2eba92072ffc72ab9ce7ccb4f2b7ad45218eec974b5d5a181fc4"},"schema_version":"1.0"},"canonical_sha256":"7a458219178727243555e6978f1af584319cb3e621e376c31dcab41964596c50","source":{"kind":"arxiv","id":"2006.00587","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00587","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00587v5","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00587","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"PJCYEGIXQ4TS","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"PJCYEGIXQ4TSINKV","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"PJCYEGIX","created_at":"2026-07-05T03:27:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PJCYEGIXQ4TSINKV42LY6GXVQQ","target":"record","payload":{"canonical_record":{"source":{"id":"2006.00587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-31T19:14:03Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"d64b054152f7f779f334325cc819edf1bd28de13c4c7db2e9517a3afca82e441","abstract_canon_sha256":"8f8cc08b519f2eba92072ffc72ab9ce7ccb4f2b7ad45218eec974b5d5a181fc4"},"schema_version":"1.0"},"canonical_sha256":"7a458219178727243555e6978f1af584319cb3e621e376c31dcab41964596c50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:25.837937Z","signature_b64":"9+7jOBVXpT+7t+viVqQcrH2l90aKrMB3+mVCDhccW4wqQQRP98VBCEJVXA0cBWHDIEIvSYs3W0aoejqgCi8SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a458219178727243555e6978f1af584319cb3e621e376c31dcab41964596c50","last_reissued_at":"2026-07-05T03:27:25.837534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:25.837534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.00587","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9QWbFdVEZsxuGyYHc2NNQJcS/5Q0CzGE/nu1V8ZgjIWSxjA4QgVdoB/+CG9Tlz6pMJWhs/32Da0ys8N5Zo4KBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:14:54.967817Z"},"content_sha256":"b1f2e029a84582cb82d1a119576d4d9fc80b43e2f353c6becb12626e16b5b453","schema_version":"1.0","event_id":"sha256:b1f2e029a84582cb82d1a119576d4d9fc80b43e2f353c6becb12626e16b5b453"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PJCYEGIXQ4TSINKV42LY6GXVQQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Beining Han, Chongjie Zhang, Jianhao Wang, Jianing Ye, Zhizhou Ren","submitted_at":"2020-05-31T19:14:03Z","abstract_excerpt":"Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the representational capacity of value functions. However, the theoretical understanding of such methods is limited. In this paper, we formalize a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning. Based on this framework, we investigate linear value factorization and reveal that multi-agent Q-learning with this simple decomposition implicitly realizes a powerful counterfactual credit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00587","kind":"arxiv","version":5},"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/2006.00587/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":"2026-07-05T03:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uElT7SuizrAW3b9I/1ip8xGeUZ0zmgYpEGiwme1Nm6lWQGCN91+TDGo/xWUoyixCG6DxfCB3G/LSuEEh4Md4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:14:54.968193Z"},"content_sha256":"b266c91b53bff1b09e11826f6dcd12c5eb24a4c71cadb86a14d66773d02a72d7","schema_version":"1.0","event_id":"sha256:b266c91b53bff1b09e11826f6dcd12c5eb24a4c71cadb86a14d66773d02a72d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJCYEGIXQ4TSINKV42LY6GXVQQ/bundle.json","state_url":"https://pith.science/pith/PJCYEGIXQ4TSINKV42LY6GXVQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJCYEGIXQ4TSINKV42LY6GXVQQ/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":"2026-07-07T04:14:54Z","links":{"resolver":"https://pith.science/pith/PJCYEGIXQ4TSINKV42LY6GXVQQ","bundle":"https://pith.science/pith/PJCYEGIXQ4TSINKV42LY6GXVQQ/bundle.json","state":"https://pith.science/pith/PJCYEGIXQ4TSINKV42LY6GXVQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJCYEGIXQ4TSINKV42LY6GXVQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PJCYEGIXQ4TSINKV42LY6GXVQQ","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":"8f8cc08b519f2eba92072ffc72ab9ce7ccb4f2b7ad45218eec974b5d5a181fc4","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-31T19:14:03Z","title_canon_sha256":"d64b054152f7f779f334325cc819edf1bd28de13c4c7db2e9517a3afca82e441"},"schema_version":"1.0","source":{"id":"2006.00587","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00587","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00587v5","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00587","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"PJCYEGIXQ4TS","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"PJCYEGIXQ4TSINKV","created_at":"2026-07-05T03:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"PJCYEGIX","created_at":"2026-07-05T03:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:b266c91b53bff1b09e11826f6dcd12c5eb24a4c71cadb86a14d66773d02a72d7","target":"graph","created_at":"2026-07-05T03:27:25Z","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/2006.00587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the representational capacity of value functions. However, the theoretical understanding of such methods is limited. In this paper, we formalize a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning. Based on this framework, we investigate linear value factorization and reveal that multi-agent Q-learning with this simple decomposition implicitly realizes a powerful counterfactual credit","authors_text":"Beining Han, Chongjie Zhang, Jianhao Wang, Jianing Ye, Zhizhou Ren","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-31T19:14:03Z","title":"Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00587","kind":"arxiv","version":5},"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:b1f2e029a84582cb82d1a119576d4d9fc80b43e2f353c6becb12626e16b5b453","target":"record","created_at":"2026-07-05T03:27:25Z","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":"8f8cc08b519f2eba92072ffc72ab9ce7ccb4f2b7ad45218eec974b5d5a181fc4","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-31T19:14:03Z","title_canon_sha256":"d64b054152f7f779f334325cc819edf1bd28de13c4c7db2e9517a3afca82e441"},"schema_version":"1.0","source":{"id":"2006.00587","kind":"arxiv","version":5}},"canonical_sha256":"7a458219178727243555e6978f1af584319cb3e621e376c31dcab41964596c50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a458219178727243555e6978f1af584319cb3e621e376c31dcab41964596c50","first_computed_at":"2026-07-05T03:27:25.837534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:25.837534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9+7jOBVXpT+7t+viVqQcrH2l90aKrMB3+mVCDhccW4wqQQRP98VBCEJVXA0cBWHDIEIvSYs3W0aoejqgCi8SDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:25.837937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.00587","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1f2e029a84582cb82d1a119576d4d9fc80b43e2f353c6becb12626e16b5b453","sha256:b266c91b53bff1b09e11826f6dcd12c5eb24a4c71cadb86a14d66773d02a72d7"],"state_sha256":"047dcebc7762e59a8c9eb01ca68975f503ad4426d2a5ea880fd6ebd20e863416"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NY2ZEK8WmsuvfgrKk9YQ217+oR82p2xysCYbsYGeYrYdG2U9L+YSB43DNL19vSflqics0+7LH+Cx3kpR7o2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:14:54.970672Z","bundle_sha256":"10213aa2065602413895c17e425fb8eb6e56283a761abe4409b890fa27bf9f1a"}}