{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FOQPOZQ3M62RP6W6727JJST5PC","short_pith_number":"pith:FOQPOZQ3","canonical_record":{"source":{"id":"2007.12306","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-24T00:50:02Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"8f6c854fa52e8aafe702a5ca3ed9ea80a235fdca12472c58a82a44a31e3c23d5","abstract_canon_sha256":"c43129f36b3bdfadb49452140422fadc3d8c1cd35890832dada36839987c8f41"},"schema_version":"1.0"},"canonical_sha256":"2ba0f7661b67b517fadefebe94ca7d788d48a85357da98e3ce5d802499599418","source":{"kind":"arxiv","id":"2007.12306","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12306","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12306v4","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12306","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"pith_short_12","alias_value":"FOQPOZQ3M62R","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"pith_short_16","alias_value":"FOQPOZQ3M62RP6W6","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"pith_short_8","alias_value":"FOQPOZQ3","created_at":"2026-07-05T02:00:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FOQPOZQ3M62RP6W6727JJST5PC","target":"record","payload":{"canonical_record":{"source":{"id":"2007.12306","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-24T00:50:02Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"8f6c854fa52e8aafe702a5ca3ed9ea80a235fdca12472c58a82a44a31e3c23d5","abstract_canon_sha256":"c43129f36b3bdfadb49452140422fadc3d8c1cd35890832dada36839987c8f41"},"schema_version":"1.0"},"canonical_sha256":"2ba0f7661b67b517fadefebe94ca7d788d48a85357da98e3ce5d802499599418","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:31.309262Z","signature_b64":"47ABhhMuhDMoI12ox492dDIfviUFPLetwsojOo1zxega5k3WxRXPl42OOv0aySACaqJchrbDNMxBBAUZb6yNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ba0f7661b67b517fadefebe94ca7d788d48a85357da98e3ce5d802499599418","last_reissued_at":"2026-07-05T02:00:31.308770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:31.308770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.12306","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:00:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQvK054VlKlW0ste3pJN7uDyWoTyd6ozUTcrpY6WtAxG4cg1Xm5GKxitjBDrvO1c8BrMmtSeWheIJYT5v1oFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:13:52.849143Z"},"content_sha256":"81177e246d2ac7e4e554e3af920cd9181de3dd194cce033a1b6b347ca6540f69","schema_version":"1.0","event_id":"sha256:81177e246d2ac7e4e554e3af920cd9181de3dd194cce033a1b6b347ca6540f69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FOQPOZQ3M62RP6W6727JJST5PC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Value-Decomposition Multi-Agent Actor-Critics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jianyu Su, Peter A. Beling, Stephen Adams","submitted_at":"2020-07-24T00:50:02Z","abstract_excerpt":"The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negative function approximator and achieves the best performance, by far, on multi-agent benchmarks, StarCraft II micromanagement tasks. However, our experiments show that, in some cases, QMIX is incompatible with A2C, a training paradigm that promotes algorithm training efficiency. To obtain a reasonable trade-off between training efficiency and algorithm performance, we extend value-decomposition to actor-critics that ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12306","kind":"arxiv","version":4},"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/2007.12306/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":"2026-07-05T02:00:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXrXwulywc/xBeXQpwnUlg4TyAFtUWAmKov6W1KHv7ndZ0MPhfAqs02SEUmsYK21Xq/bn4txXXFXBUlORor8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:13:52.849663Z"},"content_sha256":"4fc18513954fa40e377f980f81abdf0de59ff0b3b9cf5cbd9110bbe88753bf07","schema_version":"1.0","event_id":"sha256:4fc18513954fa40e377f980f81abdf0de59ff0b3b9cf5cbd9110bbe88753bf07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FOQPOZQ3M62RP6W6727JJST5PC/bundle.json","state_url":"https://pith.science/pith/FOQPOZQ3M62RP6W6727JJST5PC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FOQPOZQ3M62RP6W6727JJST5PC/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":"2026-08-09T18:13:52Z","links":{"resolver":"https://pith.science/pith/FOQPOZQ3M62RP6W6727JJST5PC","bundle":"https://pith.science/pith/FOQPOZQ3M62RP6W6727JJST5PC/bundle.json","state":"https://pith.science/pith/FOQPOZQ3M62RP6W6727JJST5PC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FOQPOZQ3M62RP6W6727JJST5PC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FOQPOZQ3M62RP6W6727JJST5PC","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":"c43129f36b3bdfadb49452140422fadc3d8c1cd35890832dada36839987c8f41","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-24T00:50:02Z","title_canon_sha256":"8f6c854fa52e8aafe702a5ca3ed9ea80a235fdca12472c58a82a44a31e3c23d5"},"schema_version":"1.0","source":{"id":"2007.12306","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12306","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12306v4","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12306","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"pith_short_12","alias_value":"FOQPOZQ3M62R","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"pith_short_16","alias_value":"FOQPOZQ3M62RP6W6","created_at":"2026-07-05T02:00:31Z"},{"alias_kind":"pith_short_8","alias_value":"FOQPOZQ3","created_at":"2026-07-05T02:00:31Z"}],"graph_snapshots":[{"event_id":"sha256:4fc18513954fa40e377f980f81abdf0de59ff0b3b9cf5cbd9110bbe88753bf07","target":"graph","created_at":"2026-07-05T02:00:31Z","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/2007.12306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negative function approximator and achieves the best performance, by far, on multi-agent benchmarks, StarCraft II micromanagement tasks. However, our experiments show that, in some cases, QMIX is incompatible with A2C, a training paradigm that promotes algorithm training efficiency. To obtain a reasonable trade-off between training efficiency and algorithm performance, we extend value-decomposition to actor-critics that ar","authors_text":"Jianyu Su, Peter A. Beling, Stephen Adams","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-24T00:50:02Z","title":"Value-Decomposition Multi-Agent Actor-Critics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12306","kind":"arxiv","version":4},"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":"sha256:81177e246d2ac7e4e554e3af920cd9181de3dd194cce033a1b6b347ca6540f69","target":"record","created_at":"2026-07-05T02:00:31Z","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":"c43129f36b3bdfadb49452140422fadc3d8c1cd35890832dada36839987c8f41","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-24T00:50:02Z","title_canon_sha256":"8f6c854fa52e8aafe702a5ca3ed9ea80a235fdca12472c58a82a44a31e3c23d5"},"schema_version":"1.0","source":{"id":"2007.12306","kind":"arxiv","version":4}},"canonical_sha256":"2ba0f7661b67b517fadefebe94ca7d788d48a85357da98e3ce5d802499599418","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ba0f7661b67b517fadefebe94ca7d788d48a85357da98e3ce5d802499599418","first_computed_at":"2026-07-05T02:00:31.308770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:31.308770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"47ABhhMuhDMoI12ox492dDIfviUFPLetwsojOo1zxega5k3WxRXPl42OOv0aySACaqJchrbDNMxBBAUZb6yNCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:31.309262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.12306","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81177e246d2ac7e4e554e3af920cd9181de3dd194cce033a1b6b347ca6540f69","sha256:4fc18513954fa40e377f980f81abdf0de59ff0b3b9cf5cbd9110bbe88753bf07"],"state_sha256":"c41ace0ab455ec1bbcb53800be404376cf504cd99ae9a094bd289a91db043311"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WlBElUPbAx3RI1sbRX4+6+nRPdqOrDZLpteTAktwuWYkY8GGXdFi4QVbOnWKp7WepwGzWf0yAJ9+AFiYsEnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:13:52.853358Z","bundle_sha256":"fc9637054bde2e4047ef2c02cebb99071158a0375969d102c079e748997fa13a"}}