{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EUJIQQOSZVM2BSTFGXADBG6O2C","short_pith_number":"pith:EUJIQQOS","schema_version":"1.0","canonical_sha256":"25128841d2cd59a0ca6535c0309bced089f2066abccc76f8d36a228ed3cb1fd9","source":{"kind":"arxiv","id":"2010.09776","version":2},"attestation_state":"computed","paper":{"title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.MA","authors_text":"Alexander Cowen Rivers, Aurora Chongxi Huang, Baokuan Zhang, Daniel Graves, Daniel Palenicek, David Rusu, Dong Chen, Haitham Bou Ammar, Hongbo Zhang, Iman Fadakar, Jiannan Wu, Jianye Hao, Jiayu Miao, Julian Villella, Jun Luo, Jun Wang, Kasra Rezaee, Kimia Hassanzadeh, Kun Shao, Ming Zhou, Mohamed Elsayed, Mohsen Rohani, Montgomery Alban, Nhat Nguyen, Nicolas Perez Nieves, Peyman Yadmellat, Sanjeevan Ahilan, Seyedershad Banijamali, Weinan Zhang, Wulong Liu, Yaodong Yang, Yihan Ni, Ying Wen, Zhengang Fu, Zhengbang Zhu, Zheng Chen, Zheng Tian","submitted_at":"2020-10-19T18:26:10Z","abstract_excerpt":"Multi-agent interaction is a fundamental aspect of autonomous driving in the real world. Despite more than a decade of research and development, the problem of how to competently interact with diverse road users in diverse scenarios remains largely unsolved. Learning methods have much to offer towards solving this problem. But they require a realistic multi-agent simulator that generates diverse and competent driving interactions. To meet this need, we develop a dedicated simulation platform called SMARTS (Scalable Multi-Agent RL Training School). SMARTS supports the training, accumulation, an"},"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":"2010.09776","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2020-10-19T18:26:10Z","cross_cats_sorted":["cs.AI","cs.GT","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"67d547c2b36fd7750117694862b42a8eddb2949d8b954456d02c759ce1daa627","abstract_canon_sha256":"c03aa1eb3c44ee1c2ff9f5f0c06b618033a0fcbbb68247ea87ed15d0237e1dfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:13.611996Z","signature_b64":"/zC5vz2VLkOJRQWMnZRs3RyC/Lx9dgziRGVYnF62yugwSQokkSORId14KSLMZidtRSmoTdTgfhydmYW5TMPmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25128841d2cd59a0ca6535c0309bced089f2066abccc76f8d36a228ed3cb1fd9","last_reissued_at":"2026-07-05T01:48:13.611461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:13.611461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.MA","authors_text":"Alexander Cowen Rivers, Aurora Chongxi Huang, Baokuan Zhang, Daniel Graves, Daniel Palenicek, David Rusu, Dong Chen, Haitham Bou Ammar, Hongbo Zhang, Iman Fadakar, Jiannan Wu, Jianye Hao, Jiayu Miao, Julian Villella, Jun Luo, Jun Wang, Kasra Rezaee, Kimia Hassanzadeh, Kun Shao, Ming Zhou, Mohamed Elsayed, Mohsen Rohani, Montgomery Alban, Nhat Nguyen, Nicolas Perez Nieves, Peyman Yadmellat, Sanjeevan Ahilan, Seyedershad Banijamali, Weinan Zhang, Wulong Liu, Yaodong Yang, Yihan Ni, Ying Wen, Zhengang Fu, Zhengbang Zhu, Zheng Chen, Zheng Tian","submitted_at":"2020-10-19T18:26:10Z","abstract_excerpt":"Multi-agent interaction is a fundamental aspect of autonomous driving in the real world. Despite more than a decade of research and development, the problem of how to competently interact with diverse road users in diverse scenarios remains largely unsolved. Learning methods have much to offer towards solving this problem. But they require a realistic multi-agent simulator that generates diverse and competent driving interactions. To meet this need, we develop a dedicated simulation platform called SMARTS (Scalable Multi-Agent RL Training School). SMARTS supports the training, accumulation, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09776","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/2010.09776/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":"2010.09776","created_at":"2026-07-05T01:48:13.611522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.09776v2","created_at":"2026-07-05T01:48:13.611522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09776","created_at":"2026-07-05T01:48:13.611522+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUJIQQOSZVM2","created_at":"2026-07-05T01:48:13.611522+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUJIQQOSZVM2BSTF","created_at":"2026-07-05T01:48:13.611522+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUJIQQOS","created_at":"2026-07-05T01:48:13.611522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21587","citing_title":"FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02450","citing_title":"CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15308","citing_title":"RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17147","citing_title":"ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03125","citing_title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C","json":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C.json","graph_json":"https://pith.science/api/pith-number/EUJIQQOSZVM2BSTFGXADBG6O2C/graph.json","events_json":"https://pith.science/api/pith-number/EUJIQQOSZVM2BSTFGXADBG6O2C/events.json","paper":"https://pith.science/paper/EUJIQQOS"},"agent_actions":{"view_html":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C","download_json":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C.json","view_paper":"https://pith.science/paper/EUJIQQOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.09776&json=true","fetch_graph":"https://pith.science/api/pith-number/EUJIQQOSZVM2BSTFGXADBG6O2C/graph.json","fetch_events":"https://pith.science/api/pith-number/EUJIQQOSZVM2BSTFGXADBG6O2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C/action/storage_attestation","attest_author":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C/action/author_attestation","sign_citation":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C/action/citation_signature","submit_replication":"https://pith.science/pith/EUJIQQOSZVM2BSTFGXADBG6O2C/action/replication_record"}},"created_at":"2026-07-05T01:48:13.611522+00:00","updated_at":"2026-07-05T01:48:13.611522+00:00"}