{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FR4CGSRQ4WH53OIWDSD44QWXTJ","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":"b424fd26bd354b73406f295dbbcccc5b3d4f361f0f1b04dbeb87a9aaa00e96f9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-02-23T14:03:22Z","title_canon_sha256":"5468fb476ab43136ea7fb15da21609744ee31c29f1f046e906b5954453c6324b"},"schema_version":"1.0","source":{"id":"1802.08534","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08534","created_at":"2026-05-18T00:18:30Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08534v2","created_at":"2026-05-18T00:18:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08534","created_at":"2026-05-18T00:18:30Z"},{"alias_kind":"pith_short_12","alias_value":"FR4CGSRQ4WH5","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FR4CGSRQ4WH53OIW","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FR4CGSRQ","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:ce5703a1d69c4cdab239dea8b33f84bf28586c6379dd0c2cc886a13ed8d713de","target":"graph","created_at":"2026-05-18T00:18:30Z","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"},"paper":{"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","authors_text":"Jianye Hao, Yan Zheng, Zongzhang Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-02-23T14:03:22Z","title":"Weighted Double Deep Multiagent Reinforcement Learning in Stochastic Cooperative Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08534","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":"sha256:61e79e84f3dc886818470cca91c01d9ce48e40f40e6f4419af45e24e1e9bc1db","target":"record","created_at":"2026-05-18T00:18:30Z","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":"b424fd26bd354b73406f295dbbcccc5b3d4f361f0f1b04dbeb87a9aaa00e96f9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-02-23T14:03:22Z","title_canon_sha256":"5468fb476ab43136ea7fb15da21609744ee31c29f1f046e906b5954453c6324b"},"schema_version":"1.0","source":{"id":"1802.08534","kind":"arxiv","version":2}},"canonical_sha256":"2c78234a30e58fddb9161c87ce42d79a51d15e383b6e7647385696bd9e2a50ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c78234a30e58fddb9161c87ce42d79a51d15e383b6e7647385696bd9e2a50ff","first_computed_at":"2026-05-18T00:18:30.947782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:30.947782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ts8RANslAi2Nb8N/n6C1CWM3RxNPyRu8XZyIpATsLlNhnv53++11HHNEjeZWZiyaQXAO9Xe+Sa8Lod0JfSPlBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:30.948131Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.08534","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61e79e84f3dc886818470cca91c01d9ce48e40f40e6f4419af45e24e1e9bc1db","sha256:ce5703a1d69c4cdab239dea8b33f84bf28586c6379dd0c2cc886a13ed8d713de"],"state_sha256":"5f68ece93737007f8e3cc0c88b530c945635ba48f49284b6766263a4ce29332c"}