{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007005341,0.0001136559,0.0002071098,0.0002747264,0.00008842239,0.0000187851,0.001258618,0.00006528008,0.00003989292],"category_scores_gemma":[0.00004023935,0.0001055308,0.0001116471,0.001112183,0.0002620253,0.001031934,0.0003753728,0.0002078119,0.00002200576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001114995,"about_ca_system_score_gemma":0.0001024028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003957071,"about_ca_topic_score_gemma":0.0003757656,"domain_scores_codex":[0.998683,0.0001015493,0.0002729105,0.000237215,0.0004242892,0.0002810523],"domain_scores_gemma":[0.9989318,0.0003506253,0.0001967975,0.0003966821,0.00008269967,0.00004144006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002725894,0.0002252584,0.007097372,0.000049509,0.00003786662,0.0003016219,0.01013573,0.04075852,0.001292585,0.9228594,0.0004492147,0.0165204],"study_design_scores_gemma":[0.001437839,0.00127654,0.05594556,0.0002816082,0.00005534205,0.00004075835,0.08630398,0.8002371,0.0352069,0.004379333,0.01400079,0.000834235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4535042,0.00002775942,0.5411333,0.0001986811,0.00007666524,0.0001451511,0.000004044053,0.00001596365,0.004894198],"genre_scores_gemma":[0.9967905,0.00001848775,0.0008650768,0.00007667973,0.0000124191,2.404966e-7,0.000001620237,0.000004185366,0.002230793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.91848,"threshold_uncertainty_score":0.430342,"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."}}