{"id":"W2104641222","doi":"10.1177/105971230501300301","title":"Reinforcement Learning for RoboCup Soccer Keepaway","year":2005,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":390,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Generality; Computer science; Artificial intelligence; Learning classifier system; Benchmark (surveying); Machine learning; Task (project management); Psychology","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"],"consensus_categories":[],"category_scores_codex":[0.0003240065,0.0002483064,0.0002247243,0.0001296592,0.0003251279,0.0001662337,0.0007878341,0.0001020431,0.0001092585],"category_scores_gemma":[0.00006378473,0.0002461059,0.0001664094,0.0002121845,0.0000566728,0.0007713095,0.0002897343,0.0002896718,0.000307009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002095527,"about_ca_system_score_gemma":0.00008101299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001499996,"about_ca_topic_score_gemma":0.000004185928,"domain_scores_codex":[0.9980931,0.00004767428,0.0003966616,0.0004679125,0.0004257464,0.0005689494],"domain_scores_gemma":[0.9988121,0.0001293928,0.0002117161,0.0005068859,0.0002002297,0.0001396327],"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":[0.00001602943,0.00004696429,0.0009961713,0.000005166805,0.0000240261,0.00000489849,0.0004977155,0.9213493,0.0006962757,0.03408218,0.0008843093,0.04139692],"study_design_scores_gemma":[0.001106256,0.0007734715,0.004317374,0.00002766958,0.00006573344,0.00001139385,0.00008802991,0.9103401,0.003698291,0.00005859257,0.07897341,0.000539645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002160611,0.00004419385,0.9916484,0.0003521383,0.0002968804,0.0007363658,5.48967e-7,0.0003221587,0.004438723],"genre_scores_gemma":[0.8498898,0.000009882785,0.1321765,0.000367567,0.0001976642,0.000323979,0.00001267495,0.00003157423,0.01699037],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8594719,"threshold_uncertainty_score":0.9999991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03632614507992138,"score_gpt":0.2862749197792012,"score_spread":0.2499487746992798,"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."}}