{"id":"W2098954282","doi":"10.1109/icsmc.2011.6084216","title":"Reinforcement learning and the effects of parameter settings in the game of Chung Toi","year":2011,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Artificial neural network; Computer science; Reinforcement; Artificial intelligence; Recurrent neural network; Temporal difference learning; Machine learning; Action (physics); 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":[0.003145685,0.0007980494,0.0005019416,0.0004473798,0.0003397031,0.0008806587,0.00104887,0.000666987,0.000963821],"category_scores_gemma":[0.02335078,0.0003355036,0.0002480274,0.0002282221,0.0009174647,0.001209926,0.0007644719,0.00127479,0.0001267827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009513302,"about_ca_system_score_gemma":0.0007733473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004796369,"about_ca_topic_score_gemma":0.003332981,"domain_scores_codex":[0.9987283,0.0007003344,0.00007876035,0.0001699702,0.0001823772,0.0001401216],"domain_scores_gemma":[0.9898689,0.007950478,0.000843227,0.0004385488,0.0005697398,0.0003291426],"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":[0.001581492,0.0009108456,0.009199329,0.0002029314,0.0001481856,0.0002097273,0.0003514322,0.8950269,0.01435622,0.004688476,0.0003942274,0.07293017],"study_design_scores_gemma":[0.0000896108,0.0008885199,0.001608336,0.00002407593,0.00003215042,0.00005560454,0.00007440653,0.9856542,0.008495127,0.002690962,0.0003561317,0.00003096149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.91871,0.0001972664,0.07650682,0.0002067243,0.00006435427,0.0002086001,0.00003722949,0.000305429,0.00376355],"genre_scores_gemma":[0.9898944,0.00002691888,0.009633549,0.0000332981,0.000002827106,0.00004885437,0.00001282746,0.0000118128,0.0003354708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004796369,"threshold_uncertainty_score":0.01663613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01934206153522624,"score_gpt":0.2529023497526191,"score_spread":0.2335602882173929,"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."}}