{"id":"W182596629","doi":"","title":"Temporal difference learning applied to a high-performance game-playing program","year":2001,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Task (project management); Temporal difference learning; Artificial intelligence; Class (philosophy); Function (biology); Sequential game; Machine learning; Game design; Reinforcement learning; Game theory; Engineering; Mathematics","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":[0.001068193,0.0003176638,0.0002938543,0.0002910141,0.000313136,0.0005104452,0.0005826792,0.0005154941,0.002437052],"category_scores_gemma":[0.004540688,0.000137694,0.0002518251,0.0003196397,0.0003291003,0.0004769826,0.0004966406,0.0007153176,0.0001802415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006750594,"about_ca_system_score_gemma":0.0006071572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009023246,"about_ca_topic_score_gemma":0.006922875,"domain_scores_codex":[0.9997354,0.00008619406,0.00001630182,0.00006571497,0.00006170361,0.00003462384],"domain_scores_gemma":[0.9988356,0.0007981456,0.00004607752,0.00005202717,0.0002056406,0.00006247238],"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":[0.001373851,0.0007404227,0.004463547,0.0001764844,0.00006653828,0.0002850482,0.0003987989,0.3427238,0.0287567,0.009289369,0.00141972,0.6103056],"study_design_scores_gemma":[0.000015857,0.0001360749,0.000449255,0.000002202086,0.000005746404,0.00001817048,0.0000154419,0.9941221,0.003673372,0.001235813,0.0003212932,0.000004685099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3958881,0.0001418289,0.5965433,0.0002692558,0.0001177537,0.000190434,0.00004752661,0.001317633,0.005484221],"genre_scores_gemma":[0.9020336,0.00004033743,0.09561543,0.00005378752,0.00001047137,0.00005700742,0.00004522207,0.00003087385,0.002113164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009023246,"threshold_uncertainty_score":0.01794147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09513926961760284,"score_gpt":0.3262099561051989,"score_spread":0.231070686487596,"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."}}