{"id":"W3186212639","doi":"10.1145/3449356","title":"Transfer Reinforcement Learning for Autonomous Driving","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Modeling and Computer Simulation","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Fidelity; Computer science; Domain (mathematical analysis); Perception; Transfer of learning; Reinforcement; Artificial intelligence; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006802341,0.0001131026,0.0001183971,0.00006913355,0.0002371592,0.00002712719,0.00005823614,0.000114325,0.00001026955],"category_scores_gemma":[0.000003424745,0.0001309071,0.00005913738,0.00007157875,0.000009518678,0.000131874,0.000002954634,0.0002010594,0.000002703618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003601312,"about_ca_system_score_gemma":0.00001269136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000146001,"about_ca_topic_score_gemma":0.000003133395,"domain_scores_codex":[0.9994159,0.00001213251,0.0001884416,0.0001788832,0.00005389447,0.0001506963],"domain_scores_gemma":[0.9996494,0.00009672463,0.000007041451,0.0001696268,0.0000448983,0.00003232232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006257529,0.000009367008,0.000005615498,0.00001654935,0.00003061629,6.036145e-7,0.000179561,0.8534689,0.0001118503,0.0001935909,4.658226e-7,0.1459766],"study_design_scores_gemma":[0.0003986074,0.00005587592,0.00001723192,0.00002506688,0.00002556404,0.000003486608,0.00002656191,0.9971554,0.001022686,0.0008473362,0.0002818439,0.00014034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1257003,0.00005138317,0.8734002,0.00009929042,0.0001372357,0.00009621085,7.582769e-7,0.0004774677,0.00003716569],"genre_scores_gemma":[0.984691,0.00004882944,0.01505898,0.00005643415,0.00003731846,0.00002037063,0.00001327364,0.00002092104,0.00005291202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8589907,"threshold_uncertainty_score":0.5338235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.016745849241885,"score_gpt":0.2309992564659062,"score_spread":0.2142534072240212,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}