{"id":"W1778554682","doi":"","title":"Reinforcement learning of local shape in the game of go","year":2007,"lang":"en","type":"article","venue":"UCL Discovery (University College London)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Template; Function (biology); Artificial intelligence; Reinforcement; Computer game; Temporal difference learning; Variety (cybernetics); Machine learning; Multimedia","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":[0.00153583,0.0006589373,0.0008369324,0.0004203618,0.0003395461,0.0006900017,0.001343168,0.0008408048,0.002182015],"category_scores_gemma":[0.008115722,0.0003053352,0.0003596545,0.0002072786,0.001606239,0.001405033,0.001023228,0.0009686932,0.0003066431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001013086,"about_ca_system_score_gemma":0.0006730106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003314106,"about_ca_topic_score_gemma":0.003677709,"domain_scores_codex":[0.9995844,0.0001706893,0.00001364646,0.00008659652,0.00007875948,0.00006592473],"domain_scores_gemma":[0.9966698,0.002361147,0.0002503413,0.0001946574,0.00021706,0.0003070348],"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":[0.0006312781,0.0003626472,0.006371999,0.00008253162,0.00006166707,0.0001362837,0.0002285852,0.872176,0.009486323,0.01229239,0.0009100192,0.09726028],"study_design_scores_gemma":[0.00002624896,0.0001245938,0.0004094234,0.000003308866,0.000006348005,0.00001608707,0.00001821217,0.9936886,0.001238785,0.004274057,0.0001875016,0.00000670953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5728041,0.0001205965,0.4195522,0.0004294258,0.00002800172,0.0001480086,0.00004592788,0.0009601718,0.005911623],"genre_scores_gemma":[0.9603713,0.00002466089,0.03763619,0.0000715088,0.00000680305,0.00007391796,0.00003414776,0.00004527802,0.001736253],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003314106,"threshold_uncertainty_score":0.008122385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01524687706555709,"score_gpt":0.2284758731527574,"score_spread":0.2132289960872003,"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."}}