{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001286238,0.0005772823,0.0006737833,0.0003286786,0.0002760855,0.000510553,0.0008502002,0.0007815753,0.002518401],"category_scores_gemma":[0.005902725,0.0002815467,0.0004183105,0.0002154246,0.001043865,0.000664543,0.0009115739,0.001434942,0.0003521498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001064522,"about_ca_system_score_gemma":0.0009764936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005376573,"about_ca_topic_score_gemma":0.00257977,"domain_scores_codex":[0.9995118,0.0001892001,0.00002311793,0.00009956662,0.0001154767,0.00006080676],"domain_scores_gemma":[0.9982528,0.001185375,0.0001410003,0.0001382326,0.0002010209,0.00008154559],"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":[0.00003393827,0.00003515129,0.0002863688,0.00002215897,0.00001197032,0.00002181663,0.00002292195,0.9803793,0.0005377289,0.003256238,0.0002416421,0.01515072],"study_design_scores_gemma":[0.000005215038,0.00002018739,0.00004505969,0.000001797615,0.000001499828,0.000002529277,0.00000225878,0.9965443,0.0001700185,0.003077913,0.0001272437,0.00000201967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05309964,0.0003372983,0.9407524,0.0003697266,0.00007911976,0.0000815426,0.00004033157,0.001232827,0.00400711],"genre_scores_gemma":[0.9598548,0.0001030577,0.03763404,0.00009072715,0.00002084405,0.0001155203,0.00004595088,0.00004746588,0.002087571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005376573,"threshold_uncertainty_score":0.01069057,"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."}}