{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LYY5MGUVRUKLRH3BCF5NTQPO3X","short_pith_number":"pith:LYY5MGUV","schema_version":"1.0","canonical_sha256":"5e31d61a958d14b89f61117ad9c1eeddf7587d2e58c5020ef4e22cff319906ef","source":{"kind":"arxiv","id":"2003.10423","version":1},"attestation_state":"computed","paper":{"title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhibav Gupta, Fei Fang, Qian Long, Xiaolong Wang, Yi Wu, Zihan Zhou","submitted_at":"2020-03-23T17:49:39Z","abstract_excerpt":"In multi-agent games, the complexity of the environment can grow exponentially as the number of agents increases, so it is particularly challenging to learn good policies when the agent population is large. In this paper, we introduce Evolutionary Population Curriculum (EPC), a curriculum learning paradigm that scales up Multi-Agent Reinforcement Learning (MARL) by progressively increasing the population of training agents in a stage-wise manner. Furthermore, EPC uses an evolutionary approach to fix an objective misalignment issue throughout the curriculum: agents successfully trained in an ea"},"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":"2003.10423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-23T17:49:39Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"44a18566e272e8b93f1a4b23b998cfc3a7f4969e08f8c520cf21e2bb25576aeb","abstract_canon_sha256":"35687f40cd52760611004447d3fa8e1ec65e4b4ed6c9d3264247e774a0a2119c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:52.490388Z","signature_b64":"sWVhZC4FLBZgBN7SCOKsm8dqnAsJdrxNL/BR5UxbZMOLuBTZvyuP4q05Rli/B+dE0THKXHcMDizSM/2wsUaPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e31d61a958d14b89f61117ad9c1eeddf7587d2e58c5020ef4e22cff319906ef","last_reissued_at":"2026-07-05T00:49:52.489895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:52.489895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhibav Gupta, Fei Fang, Qian Long, Xiaolong Wang, Yi Wu, Zihan Zhou","submitted_at":"2020-03-23T17:49:39Z","abstract_excerpt":"In multi-agent games, the complexity of the environment can grow exponentially as the number of agents increases, so it is particularly challenging to learn good policies when the agent population is large. In this paper, we introduce Evolutionary Population Curriculum (EPC), a curriculum learning paradigm that scales up Multi-Agent Reinforcement Learning (MARL) by progressively increasing the population of training agents in a stage-wise manner. Furthermore, EPC uses an evolutionary approach to fix an objective misalignment issue throughout the curriculum: agents successfully trained in an ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10423","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/2003.10423/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":"2003.10423","created_at":"2026-07-05T00:49:52.489956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.10423v1","created_at":"2026-07-05T00:49:52.489956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10423","created_at":"2026-07-05T00:49:52.489956+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYY5MGUVRUKL","created_at":"2026-07-05T00:49:52.489956+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYY5MGUVRUKLRH3B","created_at":"2026-07-05T00:49:52.489956+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYY5MGUV","created_at":"2026-07-05T00:49:52.489956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24601","citing_title":"ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X","json":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X.json","graph_json":"https://pith.science/api/pith-number/LYY5MGUVRUKLRH3BCF5NTQPO3X/graph.json","events_json":"https://pith.science/api/pith-number/LYY5MGUVRUKLRH3BCF5NTQPO3X/events.json","paper":"https://pith.science/paper/LYY5MGUV"},"agent_actions":{"view_html":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X","download_json":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X.json","view_paper":"https://pith.science/paper/LYY5MGUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.10423&json=true","fetch_graph":"https://pith.science/api/pith-number/LYY5MGUVRUKLRH3BCF5NTQPO3X/graph.json","fetch_events":"https://pith.science/api/pith-number/LYY5MGUVRUKLRH3BCF5NTQPO3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X/action/storage_attestation","attest_author":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X/action/author_attestation","sign_citation":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X/action/citation_signature","submit_replication":"https://pith.science/pith/LYY5MGUVRUKLRH3BCF5NTQPO3X/action/replication_record"}},"created_at":"2026-07-05T00:49:52.489956+00:00","updated_at":"2026-07-05T00:49:52.489956+00:00"}