{"id":"W3035679825","doi":"10.24963/ijcai.2020/464","title":"Inverse Reinforcement Learning for Team Sports: Valuing Actions and Players","year":2020,"lang":"en","type":"article","venue":"","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Ranking (information retrieval); Computer science; Consistency (knowledge bases); Ice hockey; League; Action (physics); Function (biology); Artificial intelligence; Rank (graph theory); Task (project management); Value (mathematics); Reinforcement; Machine learning; Psychology; Mathematics; Engineering; Social psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001683713,0.0000781437,0.0001647547,0.00006462462,0.0001375032,0.00004590332,0.00004831744,0.00003592512,0.0007134663],"category_scores_gemma":[0.0000422246,0.0000855538,0.0000543139,0.00008972707,0.00001729755,0.0001608409,0.00002553404,0.00008475102,0.00004206868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002250846,"about_ca_system_score_gemma":0.000008766931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007003421,"about_ca_topic_score_gemma":0.000006954337,"domain_scores_codex":[0.9993386,7.280847e-7,0.0002823854,0.0002056278,0.00002171293,0.0001509057],"domain_scores_gemma":[0.9996683,0.00001408694,0.0001341029,0.00007330685,0.0000140259,0.0000961714],"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":[0.00007016157,0.00003256439,0.4168843,0.0001484441,0.0001353083,0.000002764793,0.003329304,0.1976991,0.00004419074,0.3555435,0.02237667,0.003733721],"study_design_scores_gemma":[0.0002852704,0.0000645304,0.002439924,0.000004302125,0.000005537674,7.016192e-7,0.0003848346,0.5838063,0.00002791908,0.000323773,0.4125349,0.0001220714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5628943,0.0005266784,0.1934928,0.004035885,0.0005385662,0.0007274141,0.00002504584,0.0001773511,0.237582],"genre_scores_gemma":[0.9933764,0.0003466326,0.0006746938,0.001084643,0.0001014676,0.00001108093,0.00001327325,0.00001171746,0.004380084],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4304821,"threshold_uncertainty_score":0.7811955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06365930594556346,"score_gpt":0.2347607341601833,"score_spread":0.1711014282146198,"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."}}