{"id":"W2946807670","doi":"10.1109/cig.2019.8848125","title":"Learning Policies from Human Data for Skat","year":2019,"lang":"en","type":"preprint","venue":"2019 IEEE Conference on Games (CoG)","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Counterfactual thinking; Reinforcement learning; Perfect information; Bidding; Regret; Construct (python library); Counterfactual conditional; Artificial intelligence; State (computer science); Imitation; Value (mathematics); Action (physics); Bridge (graph theory); Task (project management); Data science; Machine learning; Microeconomics; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003328847,0.0009976256,0.0006775264,0.001247602,0.0003781859,0.001204423,0.001280978,0.00168243,0.003813074],"category_scores_gemma":[0.01786357,0.0005197661,0.0005707891,0.0008571449,0.001171089,0.001609484,0.001252601,0.001755224,0.001864069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00120274,"about_ca_system_score_gemma":0.001016145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008968299,"about_ca_topic_score_gemma":0.01670179,"domain_scores_codex":[0.9981921,0.000998941,0.00006733614,0.0004571095,0.000192807,0.00009167413],"domain_scores_gemma":[0.9942052,0.003869345,0.0003770183,0.0009974373,0.0003574059,0.0001935906],"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":[0.000938122,0.0007538116,0.04422106,0.0006560981,0.0003333584,0.0002505217,0.0004511615,0.7048993,0.003281417,0.01035785,0.01911869,0.2147385],"study_design_scores_gemma":[0.00003899604,0.0001274154,0.007692551,0.0000773978,0.00001900475,0.00007153914,0.0001407771,0.9643131,0.002138912,0.02038721,0.004956592,0.00003646955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4566817,0.002670335,0.5102469,0.002524041,0.0003238667,0.0004748618,0.01001859,0.007232158,0.009827501],"genre_scores_gemma":[0.9165347,0.0003647741,0.07244464,0.0002229575,0.00003814961,0.0001494329,0.007718414,0.0001748787,0.002352135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008968299,"threshold_uncertainty_score":0.01783216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1733676294669931,"score_gpt":0.314959953163113,"score_spread":0.1415923236961198,"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."}}