{"id":"W4401422722","doi":"10.1145/3643658.3643919","title":"A Behavior-driven Development and Reinforcement Learning approach for videogame automated testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Development (topology); Artificial intelligence; Human–computer interaction; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004115244,0.0001941651,0.0001606694,0.0001781697,0.0002615336,0.0006500108,0.0003703525,0.00006825609,0.000006692445],"category_scores_gemma":[0.0001255675,0.0001726735,0.00003832821,0.000390115,0.0000305618,0.000428492,0.00037794,0.0001971804,0.00002322267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001051853,"about_ca_system_score_gemma":0.0001458354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008258809,"about_ca_topic_score_gemma":2.842937e-7,"domain_scores_codex":[0.9984391,0.00002535377,0.0003681522,0.0004776049,0.0002981018,0.0003917117],"domain_scores_gemma":[0.9993079,0.0002097605,0.00006925582,0.0002215612,0.0000881876,0.0001033179],"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":[0.00000144197,0.000009881548,0.0007421111,0.0001451496,0.00003312032,0.00000898167,0.001167694,0.9622836,0.0004254679,0.01029067,0.0002369674,0.02465496],"study_design_scores_gemma":[0.0001906038,0.0001290501,0.0004392212,0.00006699758,0.00001570917,0.00002498125,0.00005126654,0.9902897,0.0005492097,0.000008643316,0.007995682,0.0002389191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0027373,0.00005628774,0.9871719,0.00005408514,0.0001467201,0.0005375218,1.00339e-7,0.002826892,0.006469163],"genre_scores_gemma":[0.402033,0.000002003848,0.594592,0.00005287226,0.00002445038,0.0001509532,0.00001174511,0.00001690999,0.003116132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3992957,"threshold_uncertainty_score":0.704142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04646166824848585,"score_gpt":0.2825911991807369,"score_spread":0.236129530932251,"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."}}