{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006388062,0.0005936211,0.0005077993,0.0006947907,0.0003933024,0.001188571,0.002981506,0.0001950571,0.0006445402],"category_scores_gemma":[0.0004697356,0.0005846684,0.0001467276,0.001107186,0.0002563161,0.0006565018,0.0007102067,0.0008644276,0.004036595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002812037,"about_ca_system_score_gemma":0.0002123794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002344312,"about_ca_topic_score_gemma":0.000145955,"domain_scores_codex":[0.9948238,0.0001224489,0.001267592,0.001424592,0.001380285,0.0009813416],"domain_scores_gemma":[0.9973082,0.0002343626,0.0003985288,0.0008981341,0.0007356917,0.0004250838],"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":[0.0001140111,0.0003175821,0.0009423667,0.000006290578,0.00002800787,0.00004291904,0.0008677747,0.008346178,0.00984059,0.3299933,0.00003408394,0.6494669],"study_design_scores_gemma":[0.00008863163,0.001381142,0.006412697,0.0003566622,0.0000121714,0.00007313331,0.0007697775,0.7492551,0.1617557,0.07353584,0.004808409,0.001550796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3712018,0.000006750897,0.6070241,0.003646167,0.001664013,0.0007811009,0.000004422758,0.0008809793,0.01479064],"genre_scores_gemma":[0.9693337,0.00007157143,0.02793289,0.0009317478,0.0003951338,0.0003803303,0.00001763353,0.00004238584,0.0008946257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7409089,"threshold_uncertainty_score":0.9998483,"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."}}