{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4KQX6PLXJ5JSTUQG2MTECSFH6W","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":"1c9212bf76d2d41ef59197531012802bf5a6ac5d7c1e09c1eccfee036cfdd599","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T14:51:29Z","title_canon_sha256":"07a4a8eac0a33a485fd9aa133c38ab46f6bfdc8b404af15b40840bc9a9af997c"},"schema_version":"1.0","source":{"id":"2407.01343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01343","created_at":"2026-07-05T08:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01343v1","created_at":"2026-07-05T08:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01343","created_at":"2026-07-05T08:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"4KQX6PLXJ5JS","created_at":"2026-07-05T08:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"4KQX6PLXJ5JSTUQG","created_at":"2026-07-05T08:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"4KQX6PLX","created_at":"2026-07-05T08:38:46Z"}],"graph_snapshots":[{"event_id":"sha256:3a46751bf38c69a6fb39114b7c821796ad7f57335abaf650ce6d6531025f2db3","target":"graph","created_at":"2026-07-05T08:38:46Z","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/2407.01343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline multi-agent reinforcement learning (MARL) leverages static datasets of experience to learn optimal multi-agent control. However, learning from static data presents several unique challenges to overcome. In this paper, we focus on coordination failure and investigate the role of joint actions in multi-agent policy gradients with offline data, focusing on a common setting we refer to as the 'Best Response Under Data' (BRUD) approach. By using two-player polynomial games as an analytical tool, we demonstrate a simple yet overlooked failure mode of BRUD-based algorithms, which can lead to ","authors_text":"Arnu Pretorius, Callum Rhys Tilbury, Claude Formanek, Jonathan P. Shock, Louise Beyers","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T14:51:29Z","title":"Coordination Failure in Cooperative Offline MARL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01343","kind":"arxiv","version":1},"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":"sha256:64ed781b3e089335b0d753ee794f09813164b6b1c4bd2f717b200c19ca22cdf6","target":"record","created_at":"2026-07-05T08:38:46Z","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":"1c9212bf76d2d41ef59197531012802bf5a6ac5d7c1e09c1eccfee036cfdd599","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T14:51:29Z","title_canon_sha256":"07a4a8eac0a33a485fd9aa133c38ab46f6bfdc8b404af15b40840bc9a9af997c"},"schema_version":"1.0","source":{"id":"2407.01343","kind":"arxiv","version":1}},"canonical_sha256":"e2a17f3d774f5329d206d3264148a7f59ced7669a1623344608e5928822a0d3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2a17f3d774f5329d206d3264148a7f59ced7669a1623344608e5928822a0d3f","first_computed_at":"2026-07-05T08:38:46.636062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:46.636062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q5CkPTTB0zt6DLvTPXF2uiCp1scxzC5o8/ETOwi2tBwC3z/u6+fE4IfLMCh1CS8r17tyuofYNYNtSYdJPazzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:46.636577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64ed781b3e089335b0d753ee794f09813164b6b1c4bd2f717b200c19ca22cdf6","sha256:3a46751bf38c69a6fb39114b7c821796ad7f57335abaf650ce6d6531025f2db3"],"state_sha256":"cceb56aeb62db09544b774f0c2b3abb31f379f73c467ef2a78a12b84bfd2564c"}