{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B6P3RAXVPSZGEXPEEJAWPDQMMW","short_pith_number":"pith:B6P3RAXV","schema_version":"1.0","canonical_sha256":"0f9fb882f57cb2625de42241678e0c65bc256b032c3dcee9686799945fe75990","source":{"kind":"arxiv","id":"1902.07151","version":2},"attestation_state":"computed","paper":{"title":"Emergent Coordination Through Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guy Lever, Josh Merel, Nicolas Heess, Saran Tunyasuvunakool, Siqi Liu, Thore Graepel","submitted_at":"2019-02-19T17:18:14Z","abstract_excerpt":"We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based training with co-play can lead to a progression in agents' behaviors: from random, to simple ball chasing, and finally showing evidence of cooperation. Our study highlights several of the challenges encountered in large scale multi-agent training in continuous control. In particular, we demonstrate that the automatic optimization of simple shaping rewards, n"},"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":"1902.07151","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-19T17:18:14Z","cross_cats_sorted":[],"title_canon_sha256":"db027f569c7a2195d8d3014c89c3e6a88f0fe1e3a313c065dc184cef819778a3","abstract_canon_sha256":"4bcdb33797fd5b18b60bf6b32bb1c0eab2c48a6b266ee351be15283cece96596"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:45.818617Z","signature_b64":"Xrq/xN7VSm+5hPXsb7lhaiQKKlfQcdR3lRb8F4fhm9VtrT/qoWEWZ5W+KvO+ro9ixYIBEMFpvxu0OqfzNSTsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f9fb882f57cb2625de42241678e0c65bc256b032c3dcee9686799945fe75990","last_reissued_at":"2026-07-05T02:41:45.818126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:45.818126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emergent Coordination Through Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guy Lever, Josh Merel, Nicolas Heess, Saran Tunyasuvunakool, Siqi Liu, Thore Graepel","submitted_at":"2019-02-19T17:18:14Z","abstract_excerpt":"We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based training with co-play can lead to a progression in agents' behaviors: from random, to simple ball chasing, and finally showing evidence of cooperation. Our study highlights several of the challenges encountered in large scale multi-agent training in continuous control. In particular, we demonstrate that the automatic optimization of simple shaping rewards, n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07151","kind":"arxiv","version":2},"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/1902.07151/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":"1902.07151","created_at":"2026-07-05T02:41:45.818185+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.07151v2","created_at":"2026-07-05T02:41:45.818185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07151","created_at":"2026-07-05T02:41:45.818185+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6P3RAXVPSZG","created_at":"2026-07-05T02:41:45.818185+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6P3RAXVPSZGEXPE","created_at":"2026-07-05T02:41:45.818185+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6P3RAXV","created_at":"2026-07-05T02:41:45.818185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04935","citing_title":"What Type of Inference is Active Inference?","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20658","citing_title":"Expected Free Energy-based Planning as Variational Inference","ref_index":180,"is_internal_anchor":false},{"citing_arxiv_id":"1907.09467","citing_title":"Arena: a toolkit for Multi-Agent Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06864","citing_title":"Multi-Objective Multi-Agent Bandits: From Learning Efficiency to Fairness Optimization","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW","json":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW.json","graph_json":"https://pith.science/api/pith-number/B6P3RAXVPSZGEXPEEJAWPDQMMW/graph.json","events_json":"https://pith.science/api/pith-number/B6P3RAXVPSZGEXPEEJAWPDQMMW/events.json","paper":"https://pith.science/paper/B6P3RAXV"},"agent_actions":{"view_html":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW","download_json":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW.json","view_paper":"https://pith.science/paper/B6P3RAXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.07151&json=true","fetch_graph":"https://pith.science/api/pith-number/B6P3RAXVPSZGEXPEEJAWPDQMMW/graph.json","fetch_events":"https://pith.science/api/pith-number/B6P3RAXVPSZGEXPEEJAWPDQMMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW/action/storage_attestation","attest_author":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW/action/author_attestation","sign_citation":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW/action/citation_signature","submit_replication":"https://pith.science/pith/B6P3RAXVPSZGEXPEEJAWPDQMMW/action/replication_record"}},"created_at":"2026-07-05T02:41:45.818185+00:00","updated_at":"2026-07-05T02:41:45.818185+00:00"}