{"id":"W4200085643","doi":"10.1109/tvcg.2021.3139031","title":"Heterogeneous Crowd Simulation Using Parametric Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Evacuation and Crowd Dynamics","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; York University; University Health Network; Mila - Quebec Artificial Intelligence Institute; Université de Montréal; University of Victoria","funders":"National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; Ontario Research Foundation; National Science Foundation","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Generalization; Bottleneck; Crowd simulation; Parametric statistics; Variety (cybernetics); Machine learning; Crowds; Animation; Human–computer interaction","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00006517283,0.0001461101,0.0001245253,0.0002788933,0.0002146716,0.0001120856,0.00003742426,0.00009894397,0.00004329403],"category_scores_gemma":[0.00000257255,0.0001739045,0.00006543609,0.0007253202,0.00002139241,0.0001268338,0.000001310786,0.0001531717,0.000004924987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004245026,"about_ca_system_score_gemma":0.00001726859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002457485,"about_ca_topic_score_gemma":0.000006812411,"domain_scores_codex":[0.9991915,0.00005199742,0.0002495111,0.0001780059,0.0001863043,0.0001426587],"domain_scores_gemma":[0.999587,0.00006549434,0.00003479221,0.0001172062,0.0001219704,0.00007351632],"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":[0.000003907964,0.0000304918,0.00003798016,0.00003240911,0.00004084774,0.000003136611,0.000166264,0.9929331,0.00004947027,0.003982842,0.000003488104,0.002716045],"study_design_scores_gemma":[0.0003000829,0.00004850322,0.00005127068,0.00002500645,0.00003125962,0.00001471979,0.00002207973,0.996806,0.002081205,0.000045703,0.000392127,0.0001819999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1217994,0.00006243645,0.8774018,0.000002721469,0.0003675273,0.00007933909,0.000001815219,0.0002495254,0.00003541514],"genre_scores_gemma":[0.9989181,0.0003144784,0.0004307365,0.0002016262,0.00003248834,0.000004852001,0.0000178961,0.00002980139,0.00005002843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8771187,"threshold_uncertainty_score":0.7091618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02392939390108564,"score_gpt":0.2778754913803321,"score_spread":0.2539460974792465,"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."}}