{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3T6OZNOPKIHX7SLL4CQFGVLGHZ","short_pith_number":"pith:3T6OZNOP","schema_version":"1.0","canonical_sha256":"dcfcecb5cf520f7fc96be0a05355663e77f34adc628cd31344111db486747c36","source":{"kind":"arxiv","id":"2102.09812","version":1},"attestation_state":"computed","paper":{"title":"Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, Igor Gilitschenski, Lucas Liebenwein, Ryan Sander, Sertac Karaman, Tim Seyde, Wilko Schwarting","submitted_at":"2021-02-19T09:00:29Z","abstract_excerpt":"Learning competitive behaviors in multi-agent settings such as racing requires long-term reasoning about potential adversarial interactions. This paper presents Deep Latent Competition (DLC), a novel reinforcement learning algorithm that learns competitive visual control policies through self-play in imagination. The DLC agent imagines multi-agent interaction sequences in the compact latent space of a learned world model that combines a joint transition function with opponent viewpoint prediction. Imagined self-play reduces costly sample generation in the real world, while the latent represent"},"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":"2102.09812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T09:00:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b02db6f1943dc5c3547fbe549b2e730ee1301ccb75d70f83cee441e39abc820c","abstract_canon_sha256":"8df008cfe2b1b22e9750bdd7e49b1524853618c7305084291ffa4eb537c207b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:31.166396Z","signature_b64":"sIg0J4ZxCQPZ8lEKRSjrXZplOazAWV9a2hHOgn8MF2D4wK9AFCRMGi6FEhXn6+3xbzQSk0rr1qx1PuCU/AwfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcfcecb5cf520f7fc96be0a05355663e77f34adc628cd31344111db486747c36","last_reissued_at":"2026-07-05T02:16:31.165979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:31.165979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, Igor Gilitschenski, Lucas Liebenwein, Ryan Sander, Sertac Karaman, Tim Seyde, Wilko Schwarting","submitted_at":"2021-02-19T09:00:29Z","abstract_excerpt":"Learning competitive behaviors in multi-agent settings such as racing requires long-term reasoning about potential adversarial interactions. This paper presents Deep Latent Competition (DLC), a novel reinforcement learning algorithm that learns competitive visual control policies through self-play in imagination. The DLC agent imagines multi-agent interaction sequences in the compact latent space of a learned world model that combines a joint transition function with opponent viewpoint prediction. Imagined self-play reduces costly sample generation in the real world, while the latent represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09812","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/2102.09812/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":"2102.09812","created_at":"2026-07-05T02:16:31.166043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09812v1","created_at":"2026-07-05T02:16:31.166043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09812","created_at":"2026-07-05T02:16:31.166043+00:00"},{"alias_kind":"pith_short_12","alias_value":"3T6OZNOPKIHX","created_at":"2026-07-05T02:16:31.166043+00:00"},{"alias_kind":"pith_short_16","alias_value":"3T6OZNOPKIHX7SLL","created_at":"2026-07-05T02:16:31.166043+00:00"},{"alias_kind":"pith_short_8","alias_value":"3T6OZNOP","created_at":"2026-07-05T02:16:31.166043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ","json":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ.json","graph_json":"https://pith.science/api/pith-number/3T6OZNOPKIHX7SLL4CQFGVLGHZ/graph.json","events_json":"https://pith.science/api/pith-number/3T6OZNOPKIHX7SLL4CQFGVLGHZ/events.json","paper":"https://pith.science/paper/3T6OZNOP"},"agent_actions":{"view_html":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ","download_json":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ.json","view_paper":"https://pith.science/paper/3T6OZNOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09812&json=true","fetch_graph":"https://pith.science/api/pith-number/3T6OZNOPKIHX7SLL4CQFGVLGHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3T6OZNOPKIHX7SLL4CQFGVLGHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ/action/storage_attestation","attest_author":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ/action/author_attestation","sign_citation":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ/action/citation_signature","submit_replication":"https://pith.science/pith/3T6OZNOPKIHX7SLL4CQFGVLGHZ/action/replication_record"}},"created_at":"2026-07-05T02:16:31.166043+00:00","updated_at":"2026-07-05T02:16:31.166043+00:00"}