{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00405143,0.0008487946,0.001445361,0.000670585,0.0005626418,0.0008758907,0.00163056,0.001262443,0.002582935],"category_scores_gemma":[0.01110603,0.000499722,0.0005680889,0.0006117043,0.001674218,0.001385724,0.001906148,0.001678334,0.0003428544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008171374,"about_ca_system_score_gemma":0.001096116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001565697,"about_ca_topic_score_gemma":0.001326238,"domain_scores_codex":[0.998896,0.0006430679,0.00004682159,0.000111146,0.0002195806,0.00008339229],"domain_scores_gemma":[0.9905002,0.008069236,0.0003425439,0.0003688342,0.0004902346,0.0002290114],"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":[0.0001411314,0.0001281237,0.0007121281,0.0002122591,0.00005921554,0.0001129152,0.0001514564,0.8395384,0.001304207,0.07342608,0.001599284,0.08261476],"study_design_scores_gemma":[0.00003034977,0.00004212082,0.00004643221,0.000008640112,0.000004341775,0.00001308649,0.000007454831,0.9746315,0.0001988534,0.02446162,0.0005516451,0.000003900005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009295532,0.0005224517,0.987711,0.0002715145,0.00002044808,0.00005409133,0.00001056216,0.0001912751,0.001923098],"genre_scores_gemma":[0.6572089,0.0008200164,0.3368809,0.0003352938,0.0001201792,0.0007686712,0.00009451729,0.000128053,0.003643556],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00405143,"threshold_uncertainty_score":0.02142626,"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."}}