{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KFFPJ34VGKLCCNECMFDUAIWH6N","short_pith_number":"pith:KFFPJ34V","schema_version":"1.0","canonical_sha256":"514af4ef95329621348261474022c7f36d33851658bd36af6669875d55cd604e","source":{"kind":"arxiv","id":"1911.07712","version":1},"attestation_state":"computed","paper":{"title":"Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo An, Buhong Liu, Hanjiang Lai, Rundong Wang, Runsheng Yu, Xinrun Wang, Xinwen Hou, Zhenyu Shi","submitted_at":"2019-11-18T15:41:15Z","abstract_excerpt":"Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme,where all agents are trained together by the centralized valuenetwork and each agent execute its policy independently. How-ever, an issue remains open: in the centralized training process,when the environment for the team is partially observable ornon-stationary, i.e., the observation and action informationof all the agents cannot represent the global states, existingm"},"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":"1911.07712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-18T15:41:15Z","cross_cats_sorted":[],"title_canon_sha256":"713bbc6f1861b60746bce8f416f7f68ca34ec21c709000322c4e8cc276226e36","abstract_canon_sha256":"fa3177cbdd405ee8a3df7529dbf7acdf2d9003d6ef0ca5488abad9ec7e786ce5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:07.122342Z","signature_b64":"FTufvEZlWMX/i+g6OqGT+HjjfF6hrcPewlljlWc9lkjHbq093Tx8lLbZvwHQ12Y6HXxm5LQSzEG5/7EmI1QPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514af4ef95329621348261474022c7f36d33851658bd36af6669875d55cd604e","last_reissued_at":"2026-07-05T00:20:07.121878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:07.121878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo An, Buhong Liu, Hanjiang Lai, Rundong Wang, Runsheng Yu, Xinrun Wang, Xinwen Hou, Zhenyu Shi","submitted_at":"2019-11-18T15:41:15Z","abstract_excerpt":"Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme,where all agents are trained together by the centralized valuenetwork and each agent execute its policy independently. How-ever, an issue remains open: in the centralized training process,when the environment for the team is partially observable ornon-stationary, i.e., the observation and action informationof all the agents cannot represent the global states, existingm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07712","kind":"arxiv","version":1},"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/1911.07712/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":"1911.07712","created_at":"2026-07-05T00:20:07.121935+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07712v1","created_at":"2026-07-05T00:20:07.121935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07712","created_at":"2026-07-05T00:20:07.121935+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFFPJ34VGKLC","created_at":"2026-07-05T00:20:07.121935+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFFPJ34VGKLCCNEC","created_at":"2026-07-05T00:20:07.121935+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFFPJ34V","created_at":"2026-07-05T00:20:07.121935+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/KFFPJ34VGKLCCNECMFDUAIWH6N","json":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N.json","graph_json":"https://pith.science/api/pith-number/KFFPJ34VGKLCCNECMFDUAIWH6N/graph.json","events_json":"https://pith.science/api/pith-number/KFFPJ34VGKLCCNECMFDUAIWH6N/events.json","paper":"https://pith.science/paper/KFFPJ34V"},"agent_actions":{"view_html":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N","download_json":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N.json","view_paper":"https://pith.science/paper/KFFPJ34V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07712&json=true","fetch_graph":"https://pith.science/api/pith-number/KFFPJ34VGKLCCNECMFDUAIWH6N/graph.json","fetch_events":"https://pith.science/api/pith-number/KFFPJ34VGKLCCNECMFDUAIWH6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N/action/storage_attestation","attest_author":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N/action/author_attestation","sign_citation":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N/action/citation_signature","submit_replication":"https://pith.science/pith/KFFPJ34VGKLCCNECMFDUAIWH6N/action/replication_record"}},"created_at":"2026-07-05T00:20:07.121935+00:00","updated_at":"2026-07-05T00:20:07.121935+00:00"}