{"id":"W2099765827","doi":"10.1109/icsmc.2007.4414257","title":"Active exploratory q-learning for large problems","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Curse of dimensionality; Computer science; Artificial intelligence; Bellman equation; Machine learning; Robot; Action (physics); Mathematical optimization; Mathematics","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":[0.0008525581,0.0001062634,0.0001024604,0.00009861725,0.0001935405,0.00009438156,0.0004727069,0.00005631895,0.00002662169],"category_scores_gemma":[0.0001278966,0.00009690683,0.00005479102,0.0002329616,0.00001222,0.0005699599,0.0001828971,0.0001727963,0.00009410146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005252256,"about_ca_system_score_gemma":0.00003808727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001700189,"about_ca_topic_score_gemma":0.000004949721,"domain_scores_codex":[0.9988446,0.00002307931,0.0001979939,0.0002559489,0.0002203591,0.0004579804],"domain_scores_gemma":[0.999215,0.0002160519,0.00009808869,0.0002660155,0.0001190247,0.00008581326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000306051,0.00009562882,0.002530093,0.00007574375,0.00007162293,0.00001026009,0.007948869,0.4396781,0.002227821,0.5128891,0.003103053,0.03133913],"study_design_scores_gemma":[0.0009186637,0.0003626321,0.00110321,0.00002342955,0.000005777606,0.000003559806,0.0007376408,0.7675694,0.009016837,0.0008627892,0.2190405,0.0003555512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007273441,0.00001223795,0.9799817,0.0001278134,0.0002554002,0.0002909766,1.477786e-7,0.0003659015,0.01823851],"genre_scores_gemma":[0.8665081,0.000005089751,0.1246372,0.0005090889,0.0001096815,0.00003403366,0.000005580455,0.00002049399,0.008170759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8657807,"threshold_uncertainty_score":0.3951746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02611321841918703,"score_gpt":0.2715003364265079,"score_spread":0.2453871180073209,"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."}}