{"id":"W291243768","doi":"","title":"Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Generalization; Set (abstract data type); Extension (predicate logic); Reinforcement; State (computer science); Artificial intelligence; Mathematical optimization; Mathematics; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.002533169,0.0002614544,0.001258132,0.0004598348,0.0004400836,0.0003203939,0.00054725,0.00009767538,0.0001568479],"category_scores_gemma":[0.001937203,0.0001654699,0.0008462377,0.0008408602,0.0001064287,0.0001220139,0.0001266858,0.0003761089,0.00003716881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003673309,"about_ca_system_score_gemma":0.000117745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003979978,"about_ca_topic_score_gemma":0.00003278608,"domain_scores_codex":[0.9974574,0.0001846931,0.0008161598,0.0004832664,0.0006103572,0.0004480679],"domain_scores_gemma":[0.9957588,0.002527352,0.0005049499,0.0007096375,0.0003526074,0.0001466732],"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":[0.2767102,0.00003157904,0.0000774992,0.000003226131,0.0009252572,5.214133e-7,0.000136453,0.7168636,0.00005425152,0.005068104,0.00005829147,0.00007107172],"study_design_scores_gemma":[0.4680588,0.0002535688,0.000005306466,0.000002164142,0.0004800807,4.781551e-7,0.00001967831,0.5303771,0.00002451495,0.000005380115,0.0006427831,0.0001300923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01175037,0.000004020597,0.9747134,0.0002860556,0.0008566234,0.005644959,2.489421e-7,0.0003522958,0.006392008],"genre_scores_gemma":[0.9022052,0.000001040864,0.07467612,0.00009433038,0.0001208173,0.00142307,0.00001754901,0.00001524927,0.02144667],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9000373,"threshold_uncertainty_score":0.6747668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00903513300406085,"score_gpt":0.2400708871062105,"score_spread":0.2310357541021497,"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."}}