{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008557807,0.00006622735,0.00007387623,0.00008009496,0.00006329795,0.00002072611,0.00002198292,0.00002094058,0.00002403471],"category_scores_gemma":[0.00001354947,0.00005718567,0.00001511764,0.0001959566,0.00001446177,0.00002054138,0.000003338733,0.00004577793,0.000007220524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001660031,"about_ca_system_score_gemma":0.000008984299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000261203,"about_ca_topic_score_gemma":0.00001305676,"domain_scores_codex":[0.9995844,0.000002205764,0.0001357068,0.00008723005,0.00005613375,0.0001343601],"domain_scores_gemma":[0.9998155,0.00005448062,0.0000126964,0.00006235084,0.00002449657,0.00003049798],"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":[0.000002080443,0.00000572096,0.001143032,0.00003080308,0.00001889665,4.268544e-7,0.000615787,0.9937661,0.001552073,0.001182971,0.0000353677,0.001646745],"study_design_scores_gemma":[0.0007367799,0.00007441783,0.05277955,0.00002265619,0.00001565981,0.00000103231,0.0003313074,0.939099,0.001500531,0.00001284205,0.005269343,0.000156855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8158555,0.000001871181,0.182666,0.00004939517,0.00004411296,0.0002695032,8.260542e-7,0.0006185479,0.0004942563],"genre_scores_gemma":[0.9952096,0.000004601058,0.003739859,0.00002054937,0.000005893788,0.00009476017,0.00003334818,0.00001392374,0.0008774315],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1793541,"threshold_uncertainty_score":0.2331964,"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."}}