{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XE5WJOTMERXQJI6NDTL4A5TLW2","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":"daff835301fa730b3fc0a7023945cbbc88813c248ab0d1885fb3ec0c63588cce","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-04T09:20:59Z","title_canon_sha256":"3dbfa647d5464418ca6f7973a6a8a8aec78cb266907b7ecdc03a3fd87b6056b4"},"schema_version":"1.0","source":{"id":"2010.01523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.01523","created_at":"2026-07-05T01:40:06Z"},{"alias_kind":"arxiv_version","alias_value":"2010.01523v1","created_at":"2026-07-05T01:40:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01523","created_at":"2026-07-05T01:40:06Z"},{"alias_kind":"pith_short_12","alias_value":"XE5WJOTMERXQ","created_at":"2026-07-05T01:40:06Z"},{"alias_kind":"pith_short_16","alias_value":"XE5WJOTMERXQJI6N","created_at":"2026-07-05T01:40:06Z"},{"alias_kind":"pith_short_8","alias_value":"XE5WJOTM","created_at":"2026-07-05T01:40:06Z"}],"graph_snapshots":[{"event_id":"sha256:d2d690b9c4b0e35c5ca5aa052a40a82335ded19bd4d00b162e27a15d204f3f82","target":"graph","created_at":"2026-07-05T01:40:06Z","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/2010.01523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discover such a set of roles. To solve this problem, we propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower tempo","authors_text":"Anuj Mahajan, Bei Peng, Chongjie Zhang, Shimon Whiteson, Tarun Gupta, Tonghan Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-04T09:20:59Z","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01523","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":"sha256:315eb49a8b2fcb65c3df2439e79076df64dd7d5aac7dee06bb569ef707c37d5f","target":"record","created_at":"2026-07-05T01:40:06Z","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":"daff835301fa730b3fc0a7023945cbbc88813c248ab0d1885fb3ec0c63588cce","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-04T09:20:59Z","title_canon_sha256":"3dbfa647d5464418ca6f7973a6a8a8aec78cb266907b7ecdc03a3fd87b6056b4"},"schema_version":"1.0","source":{"id":"2010.01523","kind":"arxiv","version":1}},"canonical_sha256":"b93b64ba6c246f04a3cd1cd7c0766bb6a99510a13966e0dc40e61ecf0282e935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b93b64ba6c246f04a3cd1cd7c0766bb6a99510a13966e0dc40e61ecf0282e935","first_computed_at":"2026-07-05T01:40:06.465978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:06.465978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t4opdMbrDguK7bY91wy1oLn9zZeW2MQYh/3yAJTwQ/Ljl0i7Y2rpScacfsriaRnGIssql66GDSILFP5j9z2FBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:06.466432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.01523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:315eb49a8b2fcb65c3df2439e79076df64dd7d5aac7dee06bb569ef707c37d5f","sha256:d2d690b9c4b0e35c5ca5aa052a40a82335ded19bd4d00b162e27a15d204f3f82"],"state_sha256":"06d440de5849bc644d75fc1bc2c632bc4a7797695a1d738205cc0bb0b5bece94"}