{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003622403,0.001176912,0.000610129,0.001105971,0.0003919177,0.001131852,0.002591036,0.0009234661,0.001940464],"category_scores_gemma":[0.01157383,0.0007129924,0.001097306,0.0003690946,0.001838056,0.001114945,0.001743358,0.001905608,0.0003888124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001720985,"about_ca_system_score_gemma":0.003032305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005439464,"about_ca_topic_score_gemma":0.006089124,"domain_scores_codex":[0.996392,0.001606907,0.0002045003,0.0005492959,0.001012447,0.0002347704],"domain_scores_gemma":[0.9931564,0.004102488,0.0006472851,0.0007695752,0.001073002,0.0002512741],"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":[0.0001647889,0.0006763944,0.005293683,0.0003934485,0.0001225737,0.0003747115,0.0004915255,0.724999,0.0164939,0.04859868,0.001767171,0.2006242],"study_design_scores_gemma":[0.00002592553,0.0001148429,0.0003040603,0.00002823701,0.00001593565,0.00006735206,0.00002113143,0.9822714,0.00502145,0.01018894,0.001923413,0.00001717942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007028155,0.00004348649,0.9898458,0.0001360222,0.00001124617,0.0002271714,0.00003917445,0.001411777,0.001257172],"genre_scores_gemma":[0.2732898,0.00007619053,0.7240331,0.0001555233,0.0000127925,0.000629975,0.0001393801,0.0002637386,0.001399508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005439464,"threshold_uncertainty_score":0.01915729,"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."}}