{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WIPCOX4OGSI25MZBK5KTMPZOWL","short_pith_number":"pith:WIPCOX4O","schema_version":"1.0","canonical_sha256":"b21e275f8e3491aeb3215755363f2eb2e6ece9fa2d8914d82e2102ecc6458d0f","source":{"kind":"arxiv","id":"2408.09675","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alois Knoll, Florian R\\\"ohrbein, Florian Walter, Guang Chen, Jiayi Guan, Jing Hou, Panpan Cai, Ruiqi Zhang, Shangding Gu, Yali Du","submitted_at":"2024-08-19T03:31:20Z","abstract_excerpt":"Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain, multi-agent RL (MARL) not only need to learn the control policy but also requires consideration regarding interactions with all other agents in the environment, mutual influences among different system components, and the distribution of computational resources. This augments the complexity of algorithmic design and poses higher requirements on computational resou"},"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":"2408.09675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T03:31:20Z","cross_cats_sorted":["cs.MA","cs.RO"],"title_canon_sha256":"c7a6cb9ea86b7805d074c176cb5b3a969c6593a2bd832befb73bca68e550cfac","abstract_canon_sha256":"5180565849a04d1ddf252b33df5b3d231cc1ccb0d1fda734903839685956fdf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:35.323558Z","signature_b64":"3FEmP0Ynp9CCYnVg0MctkxXFqmf2QwCiS1p896pF5jvv/M+RDGJ67yjGtWKNdUM9V23H7W5sdtqfMsrQ0uLcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b21e275f8e3491aeb3215755363f2eb2e6ece9fa2d8914d82e2102ecc6458d0f","last_reissued_at":"2026-07-05T08:56:35.323094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:35.323094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alois Knoll, Florian R\\\"ohrbein, Florian Walter, Guang Chen, Jiayi Guan, Jing Hou, Panpan Cai, Ruiqi Zhang, Shangding Gu, Yali Du","submitted_at":"2024-08-19T03:31:20Z","abstract_excerpt":"Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain, multi-agent RL (MARL) not only need to learn the control policy but also requires consideration regarding interactions with all other agents in the environment, mutual influences among different system components, and the distribution of computational resources. This augments the complexity of algorithmic design and poses higher requirements on computational resou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09675","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/2408.09675/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":"2408.09675","created_at":"2026-07-05T08:56:35.323150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09675v1","created_at":"2026-07-05T08:56:35.323150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09675","created_at":"2026-07-05T08:56:35.323150+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIPCOX4OGSI2","created_at":"2026-07-05T08:56:35.323150+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIPCOX4OGSI25MZB","created_at":"2026-07-05T08:56:35.323150+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIPCOX4O","created_at":"2026-07-05T08:56:35.323150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24010","citing_title":"Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08064","citing_title":"Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20255","citing_title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27532","citing_title":"SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20255","citing_title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07548","citing_title":"Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL","json":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL.json","graph_json":"https://pith.science/api/pith-number/WIPCOX4OGSI25MZBK5KTMPZOWL/graph.json","events_json":"https://pith.science/api/pith-number/WIPCOX4OGSI25MZBK5KTMPZOWL/events.json","paper":"https://pith.science/paper/WIPCOX4O"},"agent_actions":{"view_html":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL","download_json":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL.json","view_paper":"https://pith.science/paper/WIPCOX4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09675&json=true","fetch_graph":"https://pith.science/api/pith-number/WIPCOX4OGSI25MZBK5KTMPZOWL/graph.json","fetch_events":"https://pith.science/api/pith-number/WIPCOX4OGSI25MZBK5KTMPZOWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL/action/storage_attestation","attest_author":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL/action/author_attestation","sign_citation":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL/action/citation_signature","submit_replication":"https://pith.science/pith/WIPCOX4OGSI25MZBK5KTMPZOWL/action/replication_record"}},"created_at":"2026-07-05T08:56:35.323150+00:00","updated_at":"2026-07-05T08:56:35.323150+00:00"}