{"id":"W1508997545","doi":"10.1609/aimag.v31i2.2227","title":"The Reinforcement Learning Competitions","year":2010,"lang":"en","type":"article","venue":"AI Magazine","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Institute of Standards and Technology; University of Southern California; Toyota Research Institute, North America; Toyota Research Institute; University of Alberta; International Business Machines Corporation","keywords":"Reinforcement learning; Competition (biology); Computer science; Reinforcement; Focus (optics); Data science; Artificial intelligence; Engineering","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":[0.02812147,0.001306077,0.001733243,0.001155458,0.002612522,0.005492331,0.00311798,0.003708015,0.01301667],"category_scores_gemma":[0.08247094,0.0005163788,0.001347997,0.001075032,0.004165762,0.006919378,0.005023416,0.006970925,0.001921183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007139361,"about_ca_system_score_gemma":0.005645982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006894547,"about_ca_topic_score_gemma":0.006540129,"domain_scores_codex":[0.9676306,0.01704049,0.001269853,0.002850322,0.009356865,0.001851894],"domain_scores_gemma":[0.9350808,0.04331014,0.002430627,0.00451651,0.01013651,0.004525431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001260788,0.0009614907,0.003993305,0.0006466505,0.0002838637,0.0002179565,0.0006971844,0.05290662,0.001481658,0.6114019,0.1064873,0.2196614],"study_design_scores_gemma":[0.0008378826,0.001371574,0.004295197,0.0005161904,0.0001357715,0.0003425577,0.0005785938,0.1946984,0.003816291,0.5313541,0.2617937,0.0002598141],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.1167714,0.01169048,0.488171,0.0476166,0.005147844,0.001930341,0.001907753,0.002007481,0.3247571],"genre_scores_gemma":[0.7883537,0.002553465,0.1390452,0.01266836,0.001754708,0.002420018,0.001990829,0.000828713,0.05038501],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02812147,"threshold_uncertainty_score":0.1487224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007611555982384794,"score_gpt":0.2427157247886484,"score_spread":0.2351041688062636,"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."}}