{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C6CWCMPC46L3PSLFDOCG4KKX5F","short_pith_number":"pith:C6CWCMPC","schema_version":"1.0","canonical_sha256":"17856131e2e797b7c9651b846e2957e950d286981222596488287e4656d71f83","source":{"kind":"arxiv","id":"2110.00304","version":2},"attestation_state":"computed","paper":{"title":"Divergence-Regularized Multi-Agent Actor-Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Kefan Su, Zongqing Lu","submitted_at":"2021-10-01T10:27:42Z","abstract_excerpt":"Entropy regularization is a popular method in reinforcement learning (RL). Although it has many advantages, it alters the RL objective of the original Markov Decision Process (MDP). Though divergence regularization has been proposed to settle this problem, it cannot be trivially applied to cooperative multi-agent reinforcement learning (MARL). In this paper, we investigate divergence regularization in cooperative MARL and propose a novel off-policy cooperative MARL framework, divergence-regularized multi-agent actor-critic (DMAC). Theoretically, we derive the update rule of DMAC which is natur"},"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":"2110.00304","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T10:27:42Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"ca46bd231b93747170939e24585ad7623599a3467c94d4a034b121f75e84504c","abstract_canon_sha256":"a577d1e930e789e19abdedca90ed27cad0105be9f0e35aa7ca2e770ce8ad662f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:22.529082Z","signature_b64":"llVJuaCak9C0KYcA5GEevuCGtm6ciOeGEZd5OXaA8nuDV8uJGcCVtlCULTVsg4SXuRMKgf/0b5os8dCA0yQhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17856131e2e797b7c9651b846e2957e950d286981222596488287e4656d71f83","last_reissued_at":"2026-07-05T04:33:22.528649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:22.528649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Divergence-Regularized Multi-Agent Actor-Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Kefan Su, Zongqing Lu","submitted_at":"2021-10-01T10:27:42Z","abstract_excerpt":"Entropy regularization is a popular method in reinforcement learning (RL). Although it has many advantages, it alters the RL objective of the original Markov Decision Process (MDP). Though divergence regularization has been proposed to settle this problem, it cannot be trivially applied to cooperative multi-agent reinforcement learning (MARL). In this paper, we investigate divergence regularization in cooperative MARL and propose a novel off-policy cooperative MARL framework, divergence-regularized multi-agent actor-critic (DMAC). Theoretically, we derive the update rule of DMAC which is natur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00304","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/2110.00304/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":"2110.00304","created_at":"2026-07-05T04:33:22.528706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.00304v2","created_at":"2026-07-05T04:33:22.528706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00304","created_at":"2026-07-05T04:33:22.528706+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6CWCMPC46L3","created_at":"2026-07-05T04:33:22.528706+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6CWCMPC46L3PSLF","created_at":"2026-07-05T04:33:22.528706+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6CWCMPC","created_at":"2026-07-05T04:33:22.528706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F","json":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F.json","graph_json":"https://pith.science/api/pith-number/C6CWCMPC46L3PSLFDOCG4KKX5F/graph.json","events_json":"https://pith.science/api/pith-number/C6CWCMPC46L3PSLFDOCG4KKX5F/events.json","paper":"https://pith.science/paper/C6CWCMPC"},"agent_actions":{"view_html":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F","download_json":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F.json","view_paper":"https://pith.science/paper/C6CWCMPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.00304&json=true","fetch_graph":"https://pith.science/api/pith-number/C6CWCMPC46L3PSLFDOCG4KKX5F/graph.json","fetch_events":"https://pith.science/api/pith-number/C6CWCMPC46L3PSLFDOCG4KKX5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F/action/storage_attestation","attest_author":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F/action/author_attestation","sign_citation":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F/action/citation_signature","submit_replication":"https://pith.science/pith/C6CWCMPC46L3PSLFDOCG4KKX5F/action/replication_record"}},"created_at":"2026-07-05T04:33:22.528706+00:00","updated_at":"2026-07-05T04:33:22.528706+00:00"}