{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008475916,0.0004718101,0.0005733386,0.0002201882,0.0002738269,0.0003469592,0.0006829743,0.0005091711,0.001400821],"category_scores_gemma":[0.00331966,0.000223417,0.0002025863,0.0001356706,0.0006816884,0.0004538231,0.0005990446,0.0009281602,0.0001367354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008225125,"about_ca_system_score_gemma":0.0009632353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007358919,"about_ca_topic_score_gemma":0.005080897,"domain_scores_codex":[0.9997601,0.0001034686,0.00001219518,0.00004266215,0.00004648774,0.00003515376],"domain_scores_gemma":[0.9987208,0.0008347277,0.000125563,0.00007727383,0.0001492175,0.00009237114],"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":[0.00006294464,0.00005121001,0.0006716202,0.00002256166,0.0000141538,0.00002764312,0.00003074422,0.9783586,0.0006270203,0.002156517,0.0002896216,0.01768735],"study_design_scores_gemma":[0.000009836617,0.00001732808,0.00005524126,0.000001636638,0.000001704203,0.000002568623,0.000003275749,0.9983328,0.0002306994,0.0012571,0.00008631531,0.000001542243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2652726,0.0003449272,0.7282676,0.0006733661,0.00005695808,0.0001085862,0.00006104542,0.001229463,0.003985442],"genre_scores_gemma":[0.9799926,0.00004489951,0.0190737,0.00004712596,0.000007936806,0.00005925435,0.00003265957,0.0000159354,0.0007259023],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007358919,"threshold_uncertainty_score":0.01463217,"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."}}