{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02228192,0.0003336915,0.0006661377,0.0002718702,0.000321489,0.0008408414,0.001958476,0.0001382162,0.0001814844],"category_scores_gemma":[0.06015547,0.0001562595,0.0002585552,0.0009849161,0.0002013802,0.0001244717,0.005080388,0.001596063,0.0000230482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009617993,"about_ca_system_score_gemma":0.0002564232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004796246,"about_ca_topic_score_gemma":0.001743157,"domain_scores_codex":[0.9895689,0.00453599,0.00212592,0.0009620613,0.002386629,0.0004204651],"domain_scores_gemma":[0.9615015,0.03495785,0.00118987,0.001859874,0.0003963088,0.00009458575],"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":[0.0001897992,0.00008486462,0.06234372,0.00002160462,0.0001370202,0.0010557,0.02819262,0.4178404,0.00002230352,0.0003039579,0.001672508,0.4881355],"study_design_scores_gemma":[0.001043069,0.0005407397,0.03432755,0.0002117252,0.0001325051,0.0005930369,0.09718889,0.8235854,0.00008891716,0.006595676,0.03496408,0.000728389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9054808,0.00009892019,0.08121948,0.001597343,0.001137155,0.00257302,0.000002751262,0.00009682901,0.007793712],"genre_scores_gemma":[0.9879346,0.00001245487,0.004654788,0.0001238721,0.00007658806,0.00009555822,8.1656e-7,0.00002603404,0.00707526],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4874071,"threshold_uncertainty_score":0.9477612,"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."}}