{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DOUMV7PJVTTZWSUYAMSGZYJ2UL","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":"a3969d54de7aeffca4c6f1ddf5132ccf5df508c94534d3b9cf008ed216c004e0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T03:27:35Z","title_canon_sha256":"1e5189228508049bd34a0ca3f182d38bef0e7dcb0715f7d59ec71d205219567c"},"schema_version":"1.0","source":{"id":"2405.08036","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08036","created_at":"2026-06-04T01:09:36Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08036v6","created_at":"2026-06-04T01:09:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08036","created_at":"2026-06-04T01:09:36Z"},{"alias_kind":"pith_short_12","alias_value":"DOUMV7PJVTTZ","created_at":"2026-06-04T01:09:36Z"},{"alias_kind":"pith_short_16","alias_value":"DOUMV7PJVTTZWSUY","created_at":"2026-06-04T01:09:36Z"},{"alias_kind":"pith_short_8","alias_value":"DOUMV7PJ","created_at":"2026-06-04T01:09:36Z"}],"graph_snapshots":[{"event_id":"sha256:c464a37405196f44aee88079974a723cadb9ef938b827f82307e31f45f61fedb","target":"graph","created_at":"2026-06-04T01:09:36Z","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/2405.08036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value function factorization is widely used in cooperative multi-agent reinforcement learning (MARL). Existing approaches often impose monotonicity constraints between the joint action value and individual action values to enable decentralized execution. However, such constraints limit the expressiveness of value factorization, restricting the range of joint action values that can be represented and hindering the learning of optimal policies. To address this, we propose Potentially Optimal Joint Actions Weighting (POW), a method that ensures optimal policy recovery where existing approximate w","authors_text":"Chang Huang, Chen Ye, Di Zhang, Guang Chen, Hai Zhang, Hongtu Zhou, Junqiao Zhao, Shatong Zhu, Ziqiao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T03:27:35Z","title":"Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08036","kind":"arxiv","version":6},"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:dc36ff182143694f0bccde85abde15518d5d677f0b81a83a55b9df4b1a2180fd","target":"record","created_at":"2026-06-04T01:09:36Z","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":"a3969d54de7aeffca4c6f1ddf5132ccf5df508c94534d3b9cf008ed216c004e0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T03:27:35Z","title_canon_sha256":"1e5189228508049bd34a0ca3f182d38bef0e7dcb0715f7d59ec71d205219567c"},"schema_version":"1.0","source":{"id":"2405.08036","kind":"arxiv","version":6}},"canonical_sha256":"1ba8cafde9ace79b4a9803246ce13aa2d90907cc400b7ba094d04fce8e092cf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ba8cafde9ace79b4a9803246ce13aa2d90907cc400b7ba094d04fce8e092cf1","first_computed_at":"2026-06-04T01:09:36.699327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:36.699327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8H84hPf+fRnlBo+0eKwcf6IES2QwVcOxJON6dSel6EYuhtv30avepWi/afUX0XOBdrMjB3CUPFlz7GN3EVguDw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:36.699908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08036","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc36ff182143694f0bccde85abde15518d5d677f0b81a83a55b9df4b1a2180fd","sha256:c464a37405196f44aee88079974a723cadb9ef938b827f82307e31f45f61fedb"],"state_sha256":"a654a7b2f912509fc0c9a4361c0552cb05821132c6dac1f89fe4573f67f924b2"}