{"id":"W4385416220","doi":"10.15607/rss.2023.xix.102","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","year":2023,"lang":"en","type":"article","venue":"","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Parameterized complexity; Reinforcement learning; Prior probability; Computer science; Artificial intelligence; Reinforcement; Machine learning; Human–computer interaction; Bayesian probability; Engineering; Algorithm; Structural 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":[0.000854151,0.0008670114,0.0008404969,0.0003331866,0.0003023441,0.000519843,0.001105819,0.0008610857,0.001905781],"category_scores_gemma":[0.004256466,0.0004896632,0.0004226261,0.0002213069,0.0009086481,0.0008105743,0.001222731,0.001632027,0.000359545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000777333,"about_ca_system_score_gemma":0.001323808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006094742,"about_ca_topic_score_gemma":0.005736729,"domain_scores_codex":[0.9996657,0.00009205837,0.00001774447,0.00008447139,0.00007598892,0.00006398433],"domain_scores_gemma":[0.9987016,0.0007654035,0.0001321297,0.0001157842,0.0001699443,0.0001151394],"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":[0.00007336598,0.00005616583,0.000785649,0.00003872104,0.00001892437,0.00004872949,0.00005204704,0.9567224,0.001708443,0.003188197,0.0006026843,0.03670467],"study_design_scores_gemma":[0.000008968909,0.00001397507,0.00004940023,0.000002348788,0.000001609527,0.000004385566,0.000002443336,0.9982941,0.0002057219,0.001311027,0.0001040417,0.00000201708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03716552,0.0001441352,0.9597313,0.0001867169,0.00002598737,0.00006130002,0.00004837765,0.0008632363,0.001773406],"genre_scores_gemma":[0.8890061,0.00007157451,0.1084789,0.0001304804,0.00002721511,0.0001529469,0.0001473276,0.00009056585,0.001894908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006094742,"threshold_uncertainty_score":0.01211858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007457785226136705,"score_gpt":0.2233900344198967,"score_spread":0.2159322491937599,"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."}}