{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O65TM7JNV6R4FDEHBTUIZYDRKQ","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":"3aae4e99219899eea3f1382938efa1253f94adc9bd2c2e4e3f403e9bcc301a24","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T19:08:47Z","title_canon_sha256":"38725f237f7d2a266816958f1f3f32aafddaff534e360b5a6cc08249c43c1ebe"},"schema_version":"1.0","source":{"id":"2010.02974","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02974","created_at":"2026-07-05T02:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02974v3","created_at":"2026-07-05T02:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02974","created_at":"2026-07-05T02:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"O65TM7JNV6R4","created_at":"2026-07-05T02:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"O65TM7JNV6R4FDEH","created_at":"2026-07-05T02:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"O65TM7JN","created_at":"2026-07-05T02:48:09Z"}],"graph_snapshots":[{"event_id":"sha256:3e6937140e4b7496a30ab5b0097f3df5c93e110491db75d21dc559c00b8748e3","target":"graph","created_at":"2026-07-05T02:48:09Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.02974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the restricted joint action value function can prevent them from solving tasks that require significant coordination between agents at a given timestep. We show that this problem can be overcome by improving the joint exploration of all agents during training. Specifically, we propose a novel MARL approach called Universal Value Exploration (UneVEn) that learns a set ","authors_text":"Anuj Mahajan, Bei Peng, Shimon Whiteson, Tarun Gupta, Wendelin B\\\"ohmer","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T19:08:47Z","title":"UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02974","kind":"arxiv","version":3},"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":"sha256:18ebedd942f5ef9cc8ecd158137c0787bd379446e70c5f8e1da09cf7173ff0df","target":"record","created_at":"2026-07-05T02:48:09Z","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":"3aae4e99219899eea3f1382938efa1253f94adc9bd2c2e4e3f403e9bcc301a24","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T19:08:47Z","title_canon_sha256":"38725f237f7d2a266816958f1f3f32aafddaff534e360b5a6cc08249c43c1ebe"},"schema_version":"1.0","source":{"id":"2010.02974","kind":"arxiv","version":3}},"canonical_sha256":"77bb367d2dafa3c28c870ce88ce071540bd5fbabd1fd5265764e516f4249fe4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77bb367d2dafa3c28c870ce88ce071540bd5fbabd1fd5265764e516f4249fe4a","first_computed_at":"2026-07-05T02:48:09.624734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:09.624734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xOMNdIPB2Hfi3bpNQRztEFkCNi2ML79k1LU+kJ0SGg0yW9371e4xaapsRT3exZHfmQ1Kb8dP54cykRp0ewJVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:09.625210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02974","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18ebedd942f5ef9cc8ecd158137c0787bd379446e70c5f8e1da09cf7173ff0df","sha256:3e6937140e4b7496a30ab5b0097f3df5c93e110491db75d21dc559c00b8748e3"],"state_sha256":"29022b4fc8ecab36e1de553c1c7cf0c2a130736da33e4140e508797a08bef837"}