{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6FCD2HM2G3UMO3BDHNVLCFIOC3","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":"93a7d009352ed22cc509304f6d04ab0aaa147b27c5896f8d8d4a628ca3416135","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-07-01T08:15:05Z","title_canon_sha256":"1a2421b5fc344db5b0ff39ef1bc689dc72f6637130635e334c456c7d93b374ee"},"schema_version":"1.0","source":{"id":"2107.00284","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00284","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00284v1","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00284","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"6FCD2HM2G3UM","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"6FCD2HM2G3UMO3BD","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"6FCD2HM2","created_at":"2026-07-05T02:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:6b4fe84f0c675537dd074a819f8bddb4c17d100dd0dacbc526fad3a6712ebb3f","target":"graph","created_at":"2026-07-05T02:54:32Z","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/2107.00284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. In this paper, a new structure for a multi-agent actor critic is proposed, and the self-attention mechanism is applied in the critic network and the value decomposition method used to solve the uneven problem. The proposed algorithm makes full use of the samples in the replay memory buffer to learn the behavior of a class of agents. First, a new update method is proposed f","authors_text":"Bei Peng, Gang Wang, Kai Liu, Yuyang Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-07-01T08:15:05Z","title":"SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00284","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:cb75fbd51313a128be76e451913584cd94fb8242e71f38fd2c931e0473572069","target":"record","created_at":"2026-07-05T02:54:32Z","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":"93a7d009352ed22cc509304f6d04ab0aaa147b27c5896f8d8d4a628ca3416135","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-07-01T08:15:05Z","title_canon_sha256":"1a2421b5fc344db5b0ff39ef1bc689dc72f6637130635e334c456c7d93b374ee"},"schema_version":"1.0","source":{"id":"2107.00284","kind":"arxiv","version":1}},"canonical_sha256":"f1443d1d9a36e8c76c233b6ab1150e16c18cb6dae622531ccf5e61520a625426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1443d1d9a36e8c76c233b6ab1150e16c18cb6dae622531ccf5e61520a625426","first_computed_at":"2026-07-05T02:54:32.331065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:32.331065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bS1KAMWaGvnmy9R5YhDLqt+4PR9066aREIIwv0hdYmgn+XNdp4Bvg+oCX9IFhZFIMEJSmwymXOudvCRdVcavDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:32.331513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.00284","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb75fbd51313a128be76e451913584cd94fb8242e71f38fd2c931e0473572069","sha256:6b4fe84f0c675537dd074a819f8bddb4c17d100dd0dacbc526fad3a6712ebb3f"],"state_sha256":"7431a0c0d75d373c799ecbc95d71abd6f73ec76a3dfcdcab6396f29a3adc52ff"}