{"id":"W4289080355","doi":"10.1080/23249935.2022.2061081","title":"Multiagent modeling of pedestrian-vehicle conflicts using Adversarial Inverse Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"Transportmetrica A Transport Science","topic":"Traffic and Road Safety","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Collision avoidance; Reinforcement learning; Pedestrian; Computer science; Artificial intelligence; Adversarial system; Collision; Machine learning; Computer security; Engineering; Transport 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":[0.0005961169,0.0007306621,0.0007103064,0.000328177,0.0003038583,0.0005031221,0.0009413841,0.0007005442,0.00137203],"category_scores_gemma":[0.001573553,0.0003823393,0.0005477105,0.0002048822,0.0007345127,0.0005441308,0.0007557084,0.0009807948,0.0001326702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008844265,"about_ca_system_score_gemma":0.0008569685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01684106,"about_ca_topic_score_gemma":0.01033639,"domain_scores_codex":[0.9997765,0.00007125944,0.000008231126,0.00005225219,0.00004106699,0.00005056338],"domain_scores_gemma":[0.9992256,0.0004104794,0.0001630697,0.00003200015,0.00009514538,0.00007361786],"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":[0.00001021212,0.000008295056,0.0004217554,0.000004978157,0.000007825513,0.00002495424,0.00001188057,0.9965198,0.0001392684,0.001573247,0.00007609537,0.001201758],"study_design_scores_gemma":[8.288242e-7,0.000002554722,0.0000348891,3.88161e-7,8.670377e-7,0.000001433836,0.00000112945,0.9996215,0.00001642115,0.0003006368,0.00001863465,6.412902e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2181529,0.0003731461,0.7737474,0.0004523296,0.0000748419,0.00005947594,0.00009906707,0.0003107342,0.006730185],"genre_scores_gemma":[0.9885116,0.00005940581,0.009298537,0.00004205202,0.00001066449,0.00003747346,0.00003448051,0.00001272985,0.001993111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01684106,"threshold_uncertainty_score":0.03348607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0328431867682801,"score_gpt":0.2319418393667528,"score_spread":0.1990986525984727,"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."}}