{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NLRW4SCCLTWY5JDNBNOA5HQMNP","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":"4929f007a1fbd30713bbdf7f44cecf02d997b8c7c0f0466d3e94eca29a4d522a","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-06T03:41:08Z","title_canon_sha256":"cb07ee540e6da9fa96f7e808d19c8bda952f2591172809aff3fc578a17e1955b"},"schema_version":"1.0","source":{"id":"2212.02733","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.02733","created_at":"2026-07-05T09:10:28Z"},{"alias_kind":"arxiv_version","alias_value":"2212.02733v3","created_at":"2026-07-05T09:10:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02733","created_at":"2026-07-05T09:10:28Z"},{"alias_kind":"pith_short_12","alias_value":"NLRW4SCCLTWY","created_at":"2026-07-05T09:10:28Z"},{"alias_kind":"pith_short_16","alias_value":"NLRW4SCCLTWY5JDN","created_at":"2026-07-05T09:10:28Z"},{"alias_kind":"pith_short_8","alias_value":"NLRW4SCC","created_at":"2026-07-05T09:10:28Z"}],"graph_snapshots":[{"event_id":"sha256:82ddaffe228a56f9c904f0ebb49c84834eba5acdcafb9ca7bdaceaff5ce128f8","target":"graph","created_at":"2026-07-05T09:10:28Z","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/2212.02733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Relative overgeneralization (RO) is a pathology that can arise in cooperative multi-agent tasks when the optimal joint action's utility falls below that of a sub-optimal joint action. RO can cause the agents to get stuck into local optima or fail to solve cooperative tasks requiring significant coordination between agents within a given timestep. In this work, we empirically find that, in multi-agent reinforcement learning (MARL), both value-based and policy gradient MARL algorithms can suffer from RO and fail to learn effective coordination policies. To better overcome RO, we propose a novel ","authors_text":"Bei Peng, Lin Shi, Qiyuan Liu","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-06T03:41:08Z","title":"CURO: Curriculum Learning for Relative Overgeneralization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02733","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:f8ad8b225b1ffd90934d2a13ec10f10c2cbd7e5b47f8690014b515fd004ac634","target":"record","created_at":"2026-07-05T09:10:28Z","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":"4929f007a1fbd30713bbdf7f44cecf02d997b8c7c0f0466d3e94eca29a4d522a","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-06T03:41:08Z","title_canon_sha256":"cb07ee540e6da9fa96f7e808d19c8bda952f2591172809aff3fc578a17e1955b"},"schema_version":"1.0","source":{"id":"2212.02733","kind":"arxiv","version":3}},"canonical_sha256":"6ae36e48425ced8ea46d0b5c0e9e0c6bd75ea56f894743a985bd59ddbbbd1563","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ae36e48425ced8ea46d0b5c0e9e0c6bd75ea56f894743a985bd59ddbbbd1563","first_computed_at":"2026-07-05T09:10:28.779628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:28.779628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BWPu5CGSa+igaTDjkWylfwkMolBERs3XXqPUxpYX+xSnttS86IccHh1WnriDeMPBMTgIxx1Fj4a511/fQdfeCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:28.779982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.02733","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8ad8b225b1ffd90934d2a13ec10f10c2cbd7e5b47f8690014b515fd004ac634","sha256:82ddaffe228a56f9c904f0ebb49c84834eba5acdcafb9ca7bdaceaff5ce128f8"],"state_sha256":"7e3f5ff4d2411d9483916dfe1c9bae2fd2eb8116ad1bf2e0fe6bc9638fd9cf5f"}