{"id":"W4391896886","doi":"10.1080/21680566.2024.2314762","title":"Modelling motorized and non-motorized vehicle conflicts using multiagent inverse reinforcement learning approach","year":2024,"lang":"en","type":"article","venue":"Transportmetrica B Transport Dynamics","topic":"Traffic control and management","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University Canada West","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Reinforcement; Engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004179837,0.000567266,0.0005345459,0.0004125841,0.0002780074,0.0005954907,0.0007571388,0.000736921,0.001348194],"category_scores_gemma":[0.001183176,0.0003889361,0.0005723984,0.0002054585,0.0005578878,0.0005352334,0.0006651902,0.0006720393,0.0001092791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007909159,"about_ca_system_score_gemma":0.0008422065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01846465,"about_ca_topic_score_gemma":0.008478013,"domain_scores_codex":[0.9998353,0.00005413411,0.000007703681,0.00003335061,0.00003150047,0.00003798437],"domain_scores_gemma":[0.9994059,0.00030403,0.0001471848,0.00002598849,0.0000719311,0.00004501298],"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":[0.00000606226,0.000007774986,0.0003263951,0.000003978978,0.000005595051,0.00001524629,0.000008623271,0.9982648,0.0001651374,0.0006345985,0.00001927244,0.0005424754],"study_design_scores_gemma":[9.389284e-7,0.000003179485,0.00004571056,4.097644e-7,9.429252e-7,0.000001168009,0.000001944969,0.9997427,0.00002994632,0.0001515402,0.00002068647,7.827448e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3751621,0.0002371832,0.6150086,0.0002442095,0.00003910026,0.00009717349,0.0001122617,0.0002744738,0.00882502],"genre_scores_gemma":[0.9892876,0.00004632542,0.009048185,0.00001603707,0.000004653702,0.00005390247,0.00002954947,0.00001174037,0.001502091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01846465,"threshold_uncertainty_score":0.03671438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0156784005057284,"score_gpt":0.2035005589986131,"score_spread":0.1878221584928847,"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."}}