{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SMDARCSIJLOC4TPFK7IQSTQQ5R","short_pith_number":"pith:SMDARCSI","schema_version":"1.0","canonical_sha256":"9306088a484adc2e4de557d1094e10ec6651f738443fe2ba49866ccc62a0e708","source":{"kind":"arxiv","id":"2309.12951","version":1},"attestation_state":"computed","paper":{"title":"Boosting Studies of Multi-Agent Reinforcement Learning on Google Research Football Environment: the Past, Present, and Future","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Haifeng Zhang, He Jiang, Jun Wang, Weinan Zhang, Yan Song, Zheng Tian","submitted_at":"2023-09-22T15:50:07Z","abstract_excerpt":"Even though Google Research Football (GRF) was initially benchmarked and studied as a single-agent environment in its original paper, recent years have witnessed an increasing focus on its multi-agent nature by researchers utilizing it as a testbed for Multi-Agent Reinforcement Learning (MARL). However, the absence of standardized environment settings and unified evaluation metrics for multi-agent scenarios hampers the consistent understanding of various studies. Furthermore, the challenging 5-vs-5 and 11-vs-11 full-game scenarios have received limited thorough examination due to their substan"},"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":"2309.12951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-09-22T15:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"a81f5d82fe1f59fc3e8fc9d41c17ca34523568b7f1c4fd697ccf3ca30f87728a","abstract_canon_sha256":"38f06e084677fd5574272861f6d7117e02005da039cb210496930388e9830e53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:19.953488Z","signature_b64":"y0J5TDeEvSwkq57WccbiVopkhOEMsWNW3BiNs67bwrqlawTcdXZVcziJixY7wuRwdFuOq9FEpv/aO3RSdA/uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9306088a484adc2e4de557d1094e10ec6651f738443fe2ba49866ccc62a0e708","last_reissued_at":"2026-07-05T06:53:19.953013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:19.953013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Studies of Multi-Agent Reinforcement Learning on Google Research Football Environment: the Past, Present, and Future","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Haifeng Zhang, He Jiang, Jun Wang, Weinan Zhang, Yan Song, Zheng Tian","submitted_at":"2023-09-22T15:50:07Z","abstract_excerpt":"Even though Google Research Football (GRF) was initially benchmarked and studied as a single-agent environment in its original paper, recent years have witnessed an increasing focus on its multi-agent nature by researchers utilizing it as a testbed for Multi-Agent Reinforcement Learning (MARL). However, the absence of standardized environment settings and unified evaluation metrics for multi-agent scenarios hampers the consistent understanding of various studies. Furthermore, the challenging 5-vs-5 and 11-vs-11 full-game scenarios have received limited thorough examination due to their substan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12951","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/2309.12951/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":"2309.12951","created_at":"2026-07-05T06:53:19.953075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.12951v1","created_at":"2026-07-05T06:53:19.953075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12951","created_at":"2026-07-05T06:53:19.953075+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMDARCSIJLOC","created_at":"2026-07-05T06:53:19.953075+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMDARCSIJLOC4TPF","created_at":"2026-07-05T06:53:19.953075+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMDARCSI","created_at":"2026-07-05T06:53:19.953075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22963","citing_title":"Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00751","citing_title":"NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05943","citing_title":"MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R","json":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R.json","graph_json":"https://pith.science/api/pith-number/SMDARCSIJLOC4TPFK7IQSTQQ5R/graph.json","events_json":"https://pith.science/api/pith-number/SMDARCSIJLOC4TPFK7IQSTQQ5R/events.json","paper":"https://pith.science/paper/SMDARCSI"},"agent_actions":{"view_html":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R","download_json":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R.json","view_paper":"https://pith.science/paper/SMDARCSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.12951&json=true","fetch_graph":"https://pith.science/api/pith-number/SMDARCSIJLOC4TPFK7IQSTQQ5R/graph.json","fetch_events":"https://pith.science/api/pith-number/SMDARCSIJLOC4TPFK7IQSTQQ5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R/action/storage_attestation","attest_author":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R/action/author_attestation","sign_citation":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R/action/citation_signature","submit_replication":"https://pith.science/pith/SMDARCSIJLOC4TPFK7IQSTQQ5R/action/replication_record"}},"created_at":"2026-07-05T06:53:19.953075+00:00","updated_at":"2026-07-05T06:53:19.953075+00:00"}