{"id":"W2153039919","doi":"10.1007/s10994-012-5280-0","title":"Temporal-difference search in computer Go","year":2012,"lang":"en","type":"article","venue":"Machine Learning","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Monte Carlo tree search; Temporal difference learning; Computer science; Search algorithm; Monte Carlo method; Bootstrapping (finance); Tree (set theory); Artificial intelligence; Reinforcement learning; Markov decision process; Beam search; Markov chain Monte Carlo; Search problem; Machine learning; Algorithm; Markov process; Mathematics; Statistics; Bayesian probability","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":[0.0007587237,0.0001370897,0.0001601458,0.000162094,0.0001150195,0.0001232613,0.0006915678,0.0000572207,0.00007117983],"category_scores_gemma":[0.00007378367,0.0001245063,0.00004128942,0.0004326001,0.00004708205,0.0004349902,0.0004668406,0.0004993384,0.0005071312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005078119,"about_ca_system_score_gemma":0.00002294022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005128784,"about_ca_topic_score_gemma":0.0000757967,"domain_scores_codex":[0.9984297,0.0002453467,0.0002430804,0.0002762816,0.0002698955,0.000535766],"domain_scores_gemma":[0.9992937,0.0001877491,0.00005323284,0.0003110037,0.00003364217,0.0001206741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002615536,0.00005696867,0.7552085,0.000006857801,0.000003028943,0.000008824315,0.00355136,0.005731523,0.0003201684,0.004641677,0.00004427469,0.2304242],"study_design_scores_gemma":[0.00006787829,0.00006364263,0.09152698,0.00002654405,9.837954e-7,0.00001352037,0.00003646572,0.9015283,0.001669668,0.0005128399,0.004340135,0.0002130757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.360989,0.0002192868,0.6365866,0.0005388499,0.0002973302,0.00008534762,2.50777e-7,0.0001777458,0.001105585],"genre_scores_gemma":[0.9600753,0.000007319912,0.03881128,0.0001976117,0.0001755306,0.00000584633,0.000002448463,0.00001133802,0.0007133055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8957968,"threshold_uncertainty_score":0.6518315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04416456190730939,"score_gpt":0.309821783679691,"score_spread":0.2656572217723816,"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."}}