{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MCGQ2XAEGJOW6WVEL5OBPDZD7S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"175eaa43bb98cca1a2c1565e6fffea3166f78af41da51761163eb8e1ab2ea519","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T12:30:47Z","title_canon_sha256":"3d3af4938888edc990edeaf36df42e3407393ea46bb8505a5075287376fdce09"},"schema_version":"1.0","source":{"id":"2012.07461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07461","created_at":"2026-07-05T01:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07461v1","created_at":"2026-07-05T01:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07461","created_at":"2026-07-05T01:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"MCGQ2XAEGJOW","created_at":"2026-07-05T01:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"MCGQ2XAEGJOW6WVE","created_at":"2026-07-05T01:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"MCGQ2XAE","created_at":"2026-07-05T01:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:d71944d3edd1d13c51e2e51cbc1e1da2ba185bc41638e3f3e09fced081d73185","target":"graph","created_at":"2026-07-05T01:59:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.07461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andr\\'as Kalapos, Csaba G\\'or, Istv\\'an Harmati, R\\'obert Moni","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T12:30:47Z","title":"Sim-to-real reinforcement learning applied to end-to-end vehicle control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07461","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c2ae7b1a170a449ee6370addc3be396fdefd5d21b55e664e7768fc616b65962","target":"record","created_at":"2026-07-05T01:59:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"175eaa43bb98cca1a2c1565e6fffea3166f78af41da51761163eb8e1ab2ea519","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T12:30:47Z","title_canon_sha256":"3d3af4938888edc990edeaf36df42e3407393ea46bb8505a5075287376fdce09"},"schema_version":"1.0","source":{"id":"2012.07461","kind":"arxiv","version":1}},"canonical_sha256":"608d0d5c04325d6f5aa45f5c178f23fcb0418e9f68956f46b50c86fbf513ea8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"608d0d5c04325d6f5aa45f5c178f23fcb0418e9f68956f46b50c86fbf513ea8a","first_computed_at":"2026-07-05T01:59:20.807383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:20.807383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vY7ZdBbOQsMbr2mlIOo9876oEE34/KGKt6x/e/RTPVTIVemlHhwoHdf/T1cRgdW/LLNcWa6sAvzeNpvgpjXnAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:20.807807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.07461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c2ae7b1a170a449ee6370addc3be396fdefd5d21b55e664e7768fc616b65962","sha256:d71944d3edd1d13c51e2e51cbc1e1da2ba185bc41638e3f3e09fced081d73185"],"state_sha256":"3e58abfe1c44bf1d43534441c213fa7012110ac4f6987c56c3fe58adb7165527"}