{"id":"W3015024833","doi":"10.36227/techrxiv.12061728.v1","title":"The Use of Reinforcement Learning in Gaming The Breakout Game Case Study","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; State (computer science); Mathematical optimization; Algorithm; 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":[0.002312917,0.0008093466,0.0006291056,0.0006336174,0.0007274744,0.001398561,0.001523474,0.001293325,0.004268585],"category_scores_gemma":[0.009455792,0.000196541,0.0004641852,0.000458513,0.0008645131,0.001637331,0.0009517116,0.001412511,0.0004197391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001161625,"about_ca_system_score_gemma":0.0008177874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01352433,"about_ca_topic_score_gemma":0.01207659,"domain_scores_codex":[0.9984609,0.0009287512,0.00005391441,0.0001690089,0.0002194711,0.0001680045],"domain_scores_gemma":[0.9944934,0.004047646,0.0002408461,0.0003482163,0.0004197049,0.0004502195],"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":[0.002583709,0.00347517,0.02526573,0.0007393952,0.0003687916,0.002261704,0.001495847,0.7160188,0.006476399,0.05622942,0.007974769,0.1771102],"study_design_scores_gemma":[0.0001281915,0.0007677866,0.003121654,0.00004544425,0.00004205962,0.0002394012,0.0004957612,0.9726382,0.003013069,0.01445143,0.005021576,0.00003542761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7726206,0.001195212,0.1866441,0.001364485,0.0002012052,0.0006404045,0.0004317426,0.0009269778,0.03597532],"genre_scores_gemma":[0.9711811,0.0001198795,0.02537281,0.00008342422,0.0000115036,0.00008939935,0.00009673623,0.00002974417,0.003015497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01352433,"threshold_uncertainty_score":0.02689123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.415620828203548,"score_gpt":0.46148283182673,"score_spread":0.04586200362318199,"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."}}