{"id":"W2141650360","doi":"10.1109/icsmc.2004.1399805","title":"Reinforcement learning and aggregation","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Robustness (evolution); Artificial intelligence; Q-learning; Machine learning; Computation; Learning classifier system; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0001611128,0.00006666707,0.00005526531,0.00005622226,0.0001059249,0.0001358926,0.0001693634,0.00002538786,0.00007106165],"category_scores_gemma":[0.00003990146,0.00006029788,0.00001426485,0.0001045357,0.00001615191,0.0004923691,0.0001557719,0.00009533484,0.0001406083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002871973,"about_ca_system_score_gemma":0.00001214713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004403381,"about_ca_topic_score_gemma":9.237489e-7,"domain_scores_codex":[0.9993676,0.00001768695,0.0001367688,0.0001495735,0.0001789615,0.0001493952],"domain_scores_gemma":[0.9996885,0.00003499129,0.00005332338,0.0001430761,0.00002940472,0.00005071993],"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":[6.525044e-7,0.000002075577,0.0008910019,0.000003076455,0.000004219272,5.47937e-7,0.0002650796,0.8565001,0.0001158819,0.06642469,0.0002237499,0.07556893],"study_design_scores_gemma":[0.0001504439,0.00005249436,0.0002420068,0.000006188204,0.000001320904,0.000005141604,0.00001410646,0.9343942,0.00121688,0.00005698851,0.06377795,0.00008222082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001218501,0.00003372801,0.9474221,0.0009037108,0.00004784879,0.00006100342,3.485384e-9,0.0001935004,0.05011954],"genre_scores_gemma":[0.8951714,0.00004593999,0.08658677,0.0003351484,0.00004620094,0.000002964303,9.370198e-7,0.000003848038,0.01780679],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8939529,"threshold_uncertainty_score":0.2458876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01118141094089683,"score_gpt":0.2448448695310357,"score_spread":0.2336634585901388,"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."}}