{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4THC63ZNFQRPT5TMM4A645UYCA","short_pith_number":"pith:4THC63ZN","schema_version":"1.0","canonical_sha256":"e4ce2f6f2d2c22f9f66c6701ee7698101eb9e6abc7ab1e7aa3a67512c74ee34a","source":{"kind":"arxiv","id":"2104.06655","version":2},"attestation_state":"computed","paper":{"title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.AI","authors_text":"Bin Li, Rui Yang, Shaochen Wang, Xin Yao, Yuan Pu","submitted_at":"2021-04-14T07:02:40Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.06655","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-14T07:02:40Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"4966465384a0a6bc4bda3e4d5ec63620f64d18e2057f439ba74beb11320b8f22","abstract_canon_sha256":"cf865426f6920b01427c063f9a427c5eaefa0078e95b729b1ce487048a94cc66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:34.081411Z","signature_b64":"BaVx07Sov9iCjr34mcE2t/ejJDjSlB4DZZD2fXrb9VXtp0jU14w/mZtSbraNNjiqOV7uJdqPocHfwpC1fbL0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ce2f6f2d2c22f9f66c6701ee7698101eb9e6abc7ab1e7aa3a67512c74ee34a","last_reissued_at":"2026-07-05T02:38:34.080908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:34.080908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.AI","authors_text":"Bin Li, Rui Yang, Shaochen Wang, Xin Yao, Yuan Pu","submitted_at":"2021-04-14T07:02:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06655","kind":"arxiv","version":2},"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/2104.06655/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.06655","created_at":"2026-07-05T02:38:34.080963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06655v2","created_at":"2026-07-05T02:38:34.080963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06655","created_at":"2026-07-05T02:38:34.080963+00:00"},{"alias_kind":"pith_short_12","alias_value":"4THC63ZNFQRP","created_at":"2026-07-05T02:38:34.080963+00:00"},{"alias_kind":"pith_short_16","alias_value":"4THC63ZNFQRPT5TM","created_at":"2026-07-05T02:38:34.080963+00:00"},{"alias_kind":"pith_short_8","alias_value":"4THC63ZN","created_at":"2026-07-05T02:38:34.080963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14264","citing_title":"Explainable Multi-Agent Reinforcement Learning for Extended Reality Codec Adaptation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA","json":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA.json","graph_json":"https://pith.science/api/pith-number/4THC63ZNFQRPT5TMM4A645UYCA/graph.json","events_json":"https://pith.science/api/pith-number/4THC63ZNFQRPT5TMM4A645UYCA/events.json","paper":"https://pith.science/paper/4THC63ZN"},"agent_actions":{"view_html":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA","download_json":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA.json","view_paper":"https://pith.science/paper/4THC63ZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06655&json=true","fetch_graph":"https://pith.science/api/pith-number/4THC63ZNFQRPT5TMM4A645UYCA/graph.json","fetch_events":"https://pith.science/api/pith-number/4THC63ZNFQRPT5TMM4A645UYCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA/action/storage_attestation","attest_author":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA/action/author_attestation","sign_citation":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA/action/citation_signature","submit_replication":"https://pith.science/pith/4THC63ZNFQRPT5TMM4A645UYCA/action/replication_record"}},"created_at":"2026-07-05T02:38:34.080963+00:00","updated_at":"2026-07-05T02:38:34.080963+00:00"}