{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MCGQ2XAEGJOW6WVEL5OBPDZD7S","short_pith_number":"pith:MCGQ2XAE","schema_version":"1.0","canonical_sha256":"608d0d5c04325d6f5aa45f5c178f23fcb0418e9f68956f46b50c86fbf513ea8a","source":{"kind":"arxiv","id":"2012.07461","version":1},"attestation_state":"computed","paper":{"title":"Sim-to-real reinforcement learning applied to end-to-end vehicle control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Kalapos, Csaba G\\'or, Istv\\'an Harmati, R\\'obert Moni","submitted_at":"2020-12-14T12:30:47Z","abstract_excerpt":"In this work, we study vision-based end-to-end reinforcement learning on vehicle control problems, such as lane following and collision avoidance. Our controller policy is able to control a small-scale robot to follow the right-hand lane of a real two-lane road, while its training was solely carried out in a simulation. Our model, realized by a simple, convolutional network, only relies on images of a forward-facing monocular camera and generates continuous actions that directly control the vehicle. To train this policy we used Proximal Policy Optimization, and to achieve the generalization ca"},"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":"2012.07461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T12:30:47Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3d3af4938888edc990edeaf36df42e3407393ea46bb8505a5075287376fdce09","abstract_canon_sha256":"175eaa43bb98cca1a2c1565e6fffea3166f78af41da51761163eb8e1ab2ea519"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:20.807807Z","signature_b64":"vY7ZdBbOQsMbr2mlIOo9876oEE34/KGKt6x/e/RTPVTIVemlHhwoHdf/T1cRgdW/LLNcWa6sAvzeNpvgpjXnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"608d0d5c04325d6f5aa45f5c178f23fcb0418e9f68956f46b50c86fbf513ea8a","last_reissued_at":"2026-07-05T01:59:20.807383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:20.807383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sim-to-real reinforcement learning applied to end-to-end vehicle control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Kalapos, Csaba G\\'or, Istv\\'an Harmati, R\\'obert Moni","submitted_at":"2020-12-14T12:30:47Z","abstract_excerpt":"In this work, we study vision-based end-to-end reinforcement learning on vehicle control problems, such as lane following and collision avoidance. Our controller policy is able to control a small-scale robot to follow the right-hand lane of a real two-lane road, while its training was solely carried out in a simulation. Our model, realized by a simple, convolutional network, only relies on images of a forward-facing monocular camera and generates continuous actions that directly control the vehicle. To train this policy we used Proximal Policy Optimization, and to achieve the generalization ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07461","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/2012.07461/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":"2012.07461","created_at":"2026-07-05T01:59:20.807441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07461v1","created_at":"2026-07-05T01:59:20.807441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07461","created_at":"2026-07-05T01:59:20.807441+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCGQ2XAEGJOW","created_at":"2026-07-05T01:59:20.807441+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCGQ2XAEGJOW6WVE","created_at":"2026-07-05T01:59:20.807441+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCGQ2XAE","created_at":"2026-07-05T01:59:20.807441+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/MCGQ2XAEGJOW6WVEL5OBPDZD7S","json":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S.json","graph_json":"https://pith.science/api/pith-number/MCGQ2XAEGJOW6WVEL5OBPDZD7S/graph.json","events_json":"https://pith.science/api/pith-number/MCGQ2XAEGJOW6WVEL5OBPDZD7S/events.json","paper":"https://pith.science/paper/MCGQ2XAE"},"agent_actions":{"view_html":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S","download_json":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S.json","view_paper":"https://pith.science/paper/MCGQ2XAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07461&json=true","fetch_graph":"https://pith.science/api/pith-number/MCGQ2XAEGJOW6WVEL5OBPDZD7S/graph.json","fetch_events":"https://pith.science/api/pith-number/MCGQ2XAEGJOW6WVEL5OBPDZD7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S/action/storage_attestation","attest_author":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S/action/author_attestation","sign_citation":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S/action/citation_signature","submit_replication":"https://pith.science/pith/MCGQ2XAEGJOW6WVEL5OBPDZD7S/action/replication_record"}},"created_at":"2026-07-05T01:59:20.807441+00:00","updated_at":"2026-07-05T01:59:20.807441+00:00"}