{"id":"W2230989868","doi":"10.1609/aiide.v6i1.12392","title":"Learning Companion Behaviors Using Reinforcement Learning in Games","year":2010,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Natural (archaeology); Human–computer interaction; Quality (philosophy); Artificial intelligence; Psychology; Social psychology; Biology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000373072,0.0003211903,0.0003282707,0.0002720063,0.0002128151,0.0007182755,0.001024885,0.0001002234,0.00004746088],"category_scores_gemma":[0.0004844914,0.0002581645,0.000132682,0.0003927941,0.0003346372,0.001633666,0.0006863786,0.001007489,0.00002811968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001147234,"about_ca_system_score_gemma":0.00005854844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001113206,"about_ca_topic_score_gemma":0.00002208309,"domain_scores_codex":[0.997651,0.00002499368,0.0007781709,0.0005934188,0.000509842,0.0004425526],"domain_scores_gemma":[0.998674,0.0001479773,0.0005044244,0.000205299,0.0003623511,0.0001059552],"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":[0.000237036,0.0007333815,0.03936102,0.00005233824,0.00005295645,0.000004986081,0.01632848,0.005386397,0.2511674,0.3315725,0.00001276315,0.3550908],"study_design_scores_gemma":[0.00005525779,0.0006969888,0.001031164,0.0004893224,0.0000122326,0.00001760056,0.009461134,0.4114296,0.5619793,0.01412997,0.0002663587,0.0004311558],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9803939,0.000006021094,0.01292058,0.0005152609,0.0004511353,0.0004149451,0.00000115448,0.00006219898,0.005234808],"genre_scores_gemma":[0.999171,0.00001847772,0.0004082916,0.00009623701,0.00003992648,0.00002684452,0.000001115299,0.00001644812,0.0002216282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4060431,"threshold_uncertainty_score":0.9999871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04254371563316466,"score_gpt":0.3028056031164624,"score_spread":0.2602618874832977,"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."}}