{"id":"W4247927622","doi":"10.36227/techrxiv.12061728","title":"The Use of Reinforcement Learning in Gaming The Breakout Game Case Study.pdf","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Breakout; Reinforcement learning; Q-learning; Computer science; Artificial neural network; Artificial intelligence; Action (physics); Value (mathematics); Machine learning; Mathematical optimization; Mathematics; Economics","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":[0.001830715,0.0005352066,0.0003489003,0.0006138936,0.0007977521,0.001409913,0.001251894,0.001129025,0.010083],"category_scores_gemma":[0.006400327,0.000148177,0.0003881122,0.0004585316,0.0006196662,0.001641632,0.0008836291,0.001020685,0.0009259779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009603918,"about_ca_system_score_gemma":0.0006491066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01364057,"about_ca_topic_score_gemma":0.01682443,"domain_scores_codex":[0.9991547,0.0004601856,0.00003058901,0.00009939692,0.0001495683,0.0001055237],"domain_scores_gemma":[0.996675,0.002356567,0.0001388518,0.0002310405,0.0003008661,0.0002976424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002647463,0.006563195,0.03886247,0.001046543,0.000371257,0.005339082,0.003354941,0.3440828,0.009474897,0.09566253,0.04347707,0.4491176],"study_design_scores_gemma":[0.0003011249,0.001687323,0.01084042,0.0001495177,0.00006877889,0.0009921171,0.002381637,0.8859155,0.008931094,0.0413134,0.04732529,0.00009383976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7057259,0.001512072,0.1829408,0.00247143,0.0003832355,0.001273259,0.0014884,0.001650472,0.1025544],"genre_scores_gemma":[0.9481891,0.0002141397,0.03902667,0.0001415177,0.00001711962,0.0001707347,0.0003774807,0.00006779005,0.01179538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01364057,"threshold_uncertainty_score":0.03373098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3751405752629731,"score_gpt":0.4511381638490228,"score_spread":0.07599758858604977,"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."}}