{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FR4CGSRQ4WH53OIWDSD44QWXTJ","short_pith_number":"pith:FR4CGSRQ","schema_version":"1.0","canonical_sha256":"2c78234a30e58fddb9161c87ce42d79a51d15e383b6e7647385696bd9e2a50ff","source":{"kind":"arxiv","id":"1802.08534","version":2},"attestation_state":"computed","paper":{"title":"Weighted Double Deep Multiagent Reinforcement Learning in Stochastic Cooperative Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Jianye Hao, Yan Zheng, Zongzhang Zhang","submitted_at":"2018-02-23T14:03:22Z","abstract_excerpt":"Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when facing with the non-stationarity due to agents update their policies simultaneously in stochastic cooperative environments. This paper extends the recently proposed weighted double estimator to the multiagent domain and propose a multiagent DRL framework, named weighted double deep Q-network (WDDQN). By utilizing the weighted double estimator and the deep neural network, WDDQN can not only reduce the bias effectively but also be extended to sc"},"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":"1802.08534","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-02-23T14:03:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5468fb476ab43136ea7fb15da21609744ee31c29f1f046e906b5954453c6324b","abstract_canon_sha256":"b424fd26bd354b73406f295dbbcccc5b3d4f361f0f1b04dbeb87a9aaa00e96f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:30.948131Z","signature_b64":"Ts8RANslAi2Nb8N/n6C1CWM3RxNPyRu8XZyIpATsLlNhnv53++11HHNEjeZWZiyaQXAO9Xe+Sa8Lod0JfSPlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c78234a30e58fddb9161c87ce42d79a51d15e383b6e7647385696bd9e2a50ff","last_reissued_at":"2026-05-18T00:18:30.947782Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:30.947782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weighted Double Deep Multiagent Reinforcement Learning in Stochastic Cooperative Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Jianye Hao, Yan Zheng, Zongzhang Zhang","submitted_at":"2018-02-23T14:03:22Z","abstract_excerpt":"Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when facing with the non-stationarity due to agents update their policies simultaneously in stochastic cooperative environments. This paper extends the recently proposed weighted double estimator to the multiagent domain and propose a multiagent DRL framework, named weighted double deep Q-network (WDDQN). By utilizing the weighted double estimator and the deep neural network, WDDQN can not only reduce the bias effectively but also be extended to sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08534","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":""},"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":"1802.08534","created_at":"2026-05-18T00:18:30.947836+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08534v2","created_at":"2026-05-18T00:18:30.947836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08534","created_at":"2026-05-18T00:18:30.947836+00:00"},{"alias_kind":"pith_short_12","alias_value":"FR4CGSRQ4WH5","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FR4CGSRQ4WH53OIW","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FR4CGSRQ","created_at":"2026-05-18T12:32:25.280505+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/FR4CGSRQ4WH53OIWDSD44QWXTJ","json":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ.json","graph_json":"https://pith.science/api/pith-number/FR4CGSRQ4WH53OIWDSD44QWXTJ/graph.json","events_json":"https://pith.science/api/pith-number/FR4CGSRQ4WH53OIWDSD44QWXTJ/events.json","paper":"https://pith.science/paper/FR4CGSRQ"},"agent_actions":{"view_html":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ","download_json":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ.json","view_paper":"https://pith.science/paper/FR4CGSRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08534&json=true","fetch_graph":"https://pith.science/api/pith-number/FR4CGSRQ4WH53OIWDSD44QWXTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FR4CGSRQ4WH53OIWDSD44QWXTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ/action/storage_attestation","attest_author":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ/action/author_attestation","sign_citation":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ/action/citation_signature","submit_replication":"https://pith.science/pith/FR4CGSRQ4WH53OIWDSD44QWXTJ/action/replication_record"}},"created_at":"2026-05-18T00:18:30.947836+00:00","updated_at":"2026-05-18T00:18:30.947836+00:00"}