{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LKJVV4DENKT32ABFDVRUJ5HN5Y","short_pith_number":"pith:LKJVV4DE","schema_version":"1.0","canonical_sha256":"5a935af0646aa7bd00251d6344f4edee15182453f385c9f079306299db007b23","source":{"kind":"arxiv","id":"2203.11653","version":1},"attestation_state":"computed","paper":{"title":"Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Eduardo Candela, Leandro Parada, Luis Marques, Panagiotis Angeloudis, Tiberiu-Andrei Georgescu, Yiannis Demiris","submitted_at":"2022-03-22T12:16:57Z","abstract_excerpt":"Autonomous Driving requires high levels of coordination and collaboration between agents. Achieving effective coordination in multi-agent systems is a difficult task that remains largely unresolved. Multi-Agent Reinforcement Learning has arisen as a powerful method to accomplish this task because it considers the interaction between agents and also allows for decentralized training -- which makes it highly scalable. However, transferring policies from simulation to the real world is a big challenge, even for single-agent applications. Multi-agent systems add additional complexities to the Sim-"},"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":"2203.11653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-03-22T12:16:57Z","cross_cats_sorted":[],"title_canon_sha256":"c108997f26196c493bcb76651c12dacfd0a9ce9243ff2a291a09ed73ccb4e12e","abstract_canon_sha256":"820864545e1de527a0cdf2f186f76ca1e7f00c03dc3d0b1a6d13bcb938004354"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:14.229344Z","signature_b64":"xNabAp+AUOK5Vjz0OegVBaMalo3ZaJCDhsjygqJx+MfnSP6Kf5NNxD+7zoy2VjJBRe7OkpS3ei4ilnU/NUqzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a935af0646aa7bd00251d6344f4edee15182453f385c9f079306299db007b23","last_reissued_at":"2026-07-05T04:07:14.228981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:14.228981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Eduardo Candela, Leandro Parada, Luis Marques, Panagiotis Angeloudis, Tiberiu-Andrei Georgescu, Yiannis Demiris","submitted_at":"2022-03-22T12:16:57Z","abstract_excerpt":"Autonomous Driving requires high levels of coordination and collaboration between agents. Achieving effective coordination in multi-agent systems is a difficult task that remains largely unresolved. Multi-Agent Reinforcement Learning has arisen as a powerful method to accomplish this task because it considers the interaction between agents and also allows for decentralized training -- which makes it highly scalable. However, transferring policies from simulation to the real world is a big challenge, even for single-agent applications. Multi-agent systems add additional complexities to the Sim-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11653","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/2203.11653/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":"2203.11653","created_at":"2026-07-05T04:07:14.229037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11653v1","created_at":"2026-07-05T04:07:14.229037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11653","created_at":"2026-07-05T04:07:14.229037+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKJVV4DENKT3","created_at":"2026-07-05T04:07:14.229037+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKJVV4DENKT32ABF","created_at":"2026-07-05T04:07:14.229037+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKJVV4DE","created_at":"2026-07-05T04:07:14.229037+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/LKJVV4DENKT32ABFDVRUJ5HN5Y","json":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y.json","graph_json":"https://pith.science/api/pith-number/LKJVV4DENKT32ABFDVRUJ5HN5Y/graph.json","events_json":"https://pith.science/api/pith-number/LKJVV4DENKT32ABFDVRUJ5HN5Y/events.json","paper":"https://pith.science/paper/LKJVV4DE"},"agent_actions":{"view_html":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y","download_json":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y.json","view_paper":"https://pith.science/paper/LKJVV4DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11653&json=true","fetch_graph":"https://pith.science/api/pith-number/LKJVV4DENKT32ABFDVRUJ5HN5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/LKJVV4DENKT32ABFDVRUJ5HN5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y/action/storage_attestation","attest_author":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y/action/author_attestation","sign_citation":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y/action/citation_signature","submit_replication":"https://pith.science/pith/LKJVV4DENKT32ABFDVRUJ5HN5Y/action/replication_record"}},"created_at":"2026-07-05T04:07:14.229037+00:00","updated_at":"2026-07-05T04:07:14.229037+00:00"}