{"id":"W3214824629","doi":"10.1109/icra46639.2022.9812407","title":"Learning Interactive Driving Policies via Data-driven Simulation","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Robotics and Automation (ICRA)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Bottleneck; Domain (mathematical analysis); Policy learning; Enhanced Data Rates for GSM Evolution; Transfer of learning; State (computer science); Machine learning; Artificial intelligence","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":[0.0006974988,0.0007000837,0.0006905799,0.0003861637,0.0003134571,0.0007632789,0.001303949,0.0009862784,0.001682629],"category_scores_gemma":[0.003381964,0.0006306743,0.0005537717,0.0002650731,0.0009059828,0.0008993243,0.00135877,0.001319566,0.0003001873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008626572,"about_ca_system_score_gemma":0.001242818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006029442,"about_ca_topic_score_gemma":0.005171039,"domain_scores_codex":[0.9997645,0.00006631802,0.00001225067,0.00006006838,0.00005967753,0.00003709603],"domain_scores_gemma":[0.9985968,0.0008680858,0.000115697,0.0001598354,0.0001565862,0.0001029398],"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":[0.00001928294,0.00001458464,0.0002324458,0.000009510392,0.000006547047,0.00001279012,0.00001063077,0.9951332,0.0004173372,0.0008844567,0.0001137119,0.003145581],"study_design_scores_gemma":[0.000002778657,0.000003855727,0.00001580578,7.215709e-7,5.980794e-7,0.000001489936,0.000001499425,0.9992002,0.0001954127,0.0004869884,0.00008974272,9.601398e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08101098,0.00009683618,0.9141341,0.0002631931,0.00004486719,0.000103678,0.0001780917,0.001581241,0.002586925],"genre_scores_gemma":[0.9275121,0.00007681839,0.07069095,0.00007645004,0.00001464816,0.0001749385,0.0002757118,0.000116978,0.001061503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006029442,"threshold_uncertainty_score":0.0119887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04795188783829782,"score_gpt":0.3178916756873683,"score_spread":0.2699397878490705,"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."}}