{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4THC63ZNFQRPT5TMM4A645UYCA","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":"cf865426f6920b01427c063f9a427c5eaefa0078e95b729b1ce487048a94cc66","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-14T07:02:40Z","title_canon_sha256":"4966465384a0a6bc4bda3e4d5ec63620f64d18e2057f439ba74beb11320b8f22"},"schema_version":"1.0","source":{"id":"2104.06655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06655","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06655v2","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06655","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"4THC63ZNFQRP","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"4THC63ZNFQRPT5TM","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"4THC63ZN","created_at":"2026-07-05T02:38:34Z"}],"graph_snapshots":[{"event_id":"sha256:0e13d64917fd2892f76359d4f8c3a29b40474aee381845ffa5b921ad704a0096","target":"graph","created_at":"2026-07-05T02:38:34Z","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/2104.06655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks. Two main promising research directions are multi-agent value function decomposition and multi-agent policy gradients. In this paper, we propose a new decomposed multi-agent soft actor-critic (mSAC) method, which effectively combines the advantages of the aforementioned two methods. The main modules include decomposed Q network architecture, discrete probabilistic policy and counterfactual advantage function (optinal). Theoretically, mSAC supports efficient off-policy learning and","authors_text":"Bin Li, Rui Yang, Shaochen Wang, Xin Yao, Yuan Pu","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-14T07:02:40Z","title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06655","kind":"arxiv","version":2},"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":"sha256:7cecf50d2a21b71e21a108ccf6c21d9b7ad207210453e256a868710c8faab277","target":"record","created_at":"2026-07-05T02:38:34Z","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":"cf865426f6920b01427c063f9a427c5eaefa0078e95b729b1ce487048a94cc66","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-14T07:02:40Z","title_canon_sha256":"4966465384a0a6bc4bda3e4d5ec63620f64d18e2057f439ba74beb11320b8f22"},"schema_version":"1.0","source":{"id":"2104.06655","kind":"arxiv","version":2}},"canonical_sha256":"e4ce2f6f2d2c22f9f66c6701ee7698101eb9e6abc7ab1e7aa3a67512c74ee34a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4ce2f6f2d2c22f9f66c6701ee7698101eb9e6abc7ab1e7aa3a67512c74ee34a","first_computed_at":"2026-07-05T02:38:34.080908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:34.080908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BaVx07Sov9iCjr34mcE2t/ejJDjSlB4DZZD2fXrb9VXtp0jU14w/mZtSbraNNjiqOV7uJdqPocHfwpC1fbL0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:34.081411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cecf50d2a21b71e21a108ccf6c21d9b7ad207210453e256a868710c8faab277","sha256:0e13d64917fd2892f76359d4f8c3a29b40474aee381845ffa5b921ad704a0096"],"state_sha256":"17b6e3788a99786bcc3e25ab3c47fc69ddb47614acd61877707006f4082d62dd"}