{"id":"W3091006519","doi":"10.1613/jair.1.12531","title":"MADRaS : Multi Agent Driving Simulator","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); University of Alberta","funders":"Indian Institute of Technology Kharagpur; Eidgenössische Technische Hochschule Zürich","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Simulation; Track (disk drive); Interface (matter); Driving simulator; Generalization; Artificial intelligence; Operating system","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":[0.001606881,0.0001055095,0.0002276532,0.0003026456,0.0001644039,0.0000631547,0.0003593164,0.0001690088,0.0003993727],"category_scores_gemma":[0.0006232449,0.0001003371,0.0001248741,0.0006078089,0.0001654888,0.0001665351,0.00009999365,0.001208581,0.0002427388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001896292,"about_ca_system_score_gemma":0.0001900622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002773051,"about_ca_topic_score_gemma":0.00004185271,"domain_scores_codex":[0.9982003,0.0001242409,0.0006208255,0.0001327128,0.0004681049,0.0004538195],"domain_scores_gemma":[0.9986585,0.0002577576,0.00005823214,0.0002409499,0.0006327175,0.000151808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003860702,0.0003394822,0.001443105,0.00006869947,0.0001979058,0.001591528,0.001259063,0.1692521,0.1905867,0.01044574,0.0007039749,0.624073],"study_design_scores_gemma":[0.00005703571,0.0001435323,0.001240574,0.0001161497,0.00001342958,0.0001870916,0.002496314,0.2730862,0.7054213,0.01119077,0.005835745,0.0002118483],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8179413,0.001612757,0.1782461,0.0007258134,0.0006508996,0.00009457984,0.000001714803,0.00009623581,0.0006305869],"genre_scores_gemma":[0.9957659,0.0006518752,0.003183203,0.0000123181,0.0002161938,0.000001813037,4.383911e-7,0.00002233328,0.0001459236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6238612,"threshold_uncertainty_score":0.525075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1355636750621388,"score_gpt":0.3935038671666261,"score_spread":0.2579401921044873,"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."}}