{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TVDR4Z7C4UG4FTKEGPOPM6RSQF","short_pith_number":"pith:TVDR4Z7C","schema_version":"1.0","canonical_sha256":"9d471e67e2e50dc2cd4433dcf67a32817823eeb38174abb95790c9b6e8ebaeea","source":{"kind":"arxiv","id":"2302.03429","version":1},"attestation_state":"computed","paper":{"title":"Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Bo An, Bowei He, Changjie Fan, Longtao Zheng, Rundong Wang, Tangjie Lv, Wei Qiu, Yingfeng Chen, Yujing Hu, Zinovi Rabinovich","submitted_at":"2023-02-07T12:30:52Z","abstract_excerpt":"Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach to resolving them is automatic curriculum learning (ACL). ACL involves a student (curriculum learner) training on tasks of increasing difficulty controlled by a teacher (curriculum generator). Despite its success, ACL's applicability is limited by (1) the lack of a general student framework for dealing with the varying number of agents across tasks and the s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.03429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-07T12:30:52Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"b4920756fb79fd90ff0b550f8049b0706bee3c459a01f88023d6a837dd4c99ff","abstract_canon_sha256":"9bbcaf676e9395ece0da422ddbf5deacbfe6b071e086803590defd476992a529"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:37.046499Z","signature_b64":"VPdEQXqGvIzSdzdaUOKFJZunDIAsdH5MISx6znKAzGz3l99ClXX2rGnVHYVX/4M4kpvPGLgKcAP17if0+nVrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d471e67e2e50dc2cd4433dcf67a32817823eeb38174abb95790c9b6e8ebaeea","last_reissued_at":"2026-07-05T05:39:37.046099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:37.046099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Bo An, Bowei He, Changjie Fan, Longtao Zheng, Rundong Wang, Tangjie Lv, Wei Qiu, Yingfeng Chen, Yujing Hu, Zinovi Rabinovich","submitted_at":"2023-02-07T12:30:52Z","abstract_excerpt":"Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach to resolving them is automatic curriculum learning (ACL). ACL involves a student (curriculum learner) training on tasks of increasing difficulty controlled by a teacher (curriculum generator). Despite its success, ACL's applicability is limited by (1) the lack of a general student framework for dealing with the varying number of agents across tasks and the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03429","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.03429/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.03429","created_at":"2026-07-05T05:39:37.046157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03429v1","created_at":"2026-07-05T05:39:37.046157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03429","created_at":"2026-07-05T05:39:37.046157+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVDR4Z7C4UG4","created_at":"2026-07-05T05:39:37.046157+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVDR4Z7C4UG4FTKE","created_at":"2026-07-05T05:39:37.046157+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVDR4Z7C","created_at":"2026-07-05T05:39:37.046157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF","json":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF.json","graph_json":"https://pith.science/api/pith-number/TVDR4Z7C4UG4FTKEGPOPM6RSQF/graph.json","events_json":"https://pith.science/api/pith-number/TVDR4Z7C4UG4FTKEGPOPM6RSQF/events.json","paper":"https://pith.science/paper/TVDR4Z7C"},"agent_actions":{"view_html":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF","download_json":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF.json","view_paper":"https://pith.science/paper/TVDR4Z7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03429&json=true","fetch_graph":"https://pith.science/api/pith-number/TVDR4Z7C4UG4FTKEGPOPM6RSQF/graph.json","fetch_events":"https://pith.science/api/pith-number/TVDR4Z7C4UG4FTKEGPOPM6RSQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF/action/storage_attestation","attest_author":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF/action/author_attestation","sign_citation":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF/action/citation_signature","submit_replication":"https://pith.science/pith/TVDR4Z7C4UG4FTKEGPOPM6RSQF/action/replication_record"}},"created_at":"2026-07-05T05:39:37.046157+00:00","updated_at":"2026-07-05T05:39:37.046157+00:00"}