{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003728834,0.0001787875,0.0001628282,0.0003197468,0.0005545247,0.0005248605,0.001277417,0.00003810784,0.0004238973],"category_scores_gemma":[0.0001886899,0.0001985238,0.00003913346,0.0002474258,0.00004129912,0.0009241198,0.001746045,0.0005001553,0.00003711684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001850366,"about_ca_system_score_gemma":0.00008256352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002171588,"about_ca_topic_score_gemma":0.000003538121,"domain_scores_codex":[0.9979505,0.0001813533,0.000367068,0.0004809618,0.0008055288,0.0002146204],"domain_scores_gemma":[0.998646,0.0002598997,0.0003777176,0.0004425147,0.0002070165,0.00006681997],"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":[0.000005608898,0.00003071525,0.0007896083,0.000004023051,0.00003947691,0.000004037499,0.0007631341,0.9162164,0.0003412263,0.07472607,0.0001252675,0.006954407],"study_design_scores_gemma":[0.0002521164,0.0001774176,0.002812338,0.00002449139,0.000008486597,0.00001094237,0.0003503248,0.9932656,0.00003119388,0.001014696,0.001844825,0.00020756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005155783,0.000006079928,0.9849523,0.00355934,0.0009709363,0.0001784803,0.000010955,0.0002497313,0.004916419],"genre_scores_gemma":[0.9881276,0.00002152576,0.009752605,0.0003542965,0.00007757291,0.000009806168,0.0002798358,0.00001493963,0.001361857],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9829718,"threshold_uncertainty_score":0.8095564,"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."}}