{"id":"W75509695","doi":"","title":"A new Q(lambda) with interim forward view and Monte Carlo equivalence","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Monte Carlo method; Markov decision process; Algorithm; Equivalence (formal languages); Q-learning; Markov process; Mathematical optimization; Artificial intelligence; Mathematics; Discrete mathematics; Statistics","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":[0.004033861,0.0009085628,0.001027834,0.001235736,0.0009097232,0.002349419,0.00318773,0.002255155,0.008540301],"category_scores_gemma":[0.01565116,0.0007992766,0.001659164,0.00117818,0.00358259,0.005100776,0.00490481,0.006115992,0.001622458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002242083,"about_ca_system_score_gemma":0.004008454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002863303,"about_ca_topic_score_gemma":0.002443943,"domain_scores_codex":[0.997184,0.0006243773,0.000197989,0.0006789151,0.001065073,0.0002495894],"domain_scores_gemma":[0.9951552,0.002065701,0.0003150362,0.0007068469,0.00134324,0.0004139411],"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":[0.00002883132,0.00006585904,0.0005647421,0.0001008833,0.00002934092,0.0001068355,0.0001546259,0.05419681,0.001751577,0.8992248,0.003379408,0.0403963],"study_design_scores_gemma":[0.00002720652,0.00007208112,0.0001914375,0.00004479381,0.00001647602,0.0001402528,0.00001992135,0.5310973,0.001167625,0.4563861,0.01080196,0.0000349205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001721766,0.0001050673,0.9925323,0.0003077997,0.0001019426,0.00003712395,0.00005566178,0.0001096484,0.005028783],"genre_scores_gemma":[0.1502254,0.0004808038,0.8360615,0.0009286797,0.000411275,0.0003364732,0.0002015881,0.0004968784,0.01085741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008540301,"threshold_uncertainty_score":0.02857018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03106032801753098,"score_gpt":0.2875444306336761,"score_spread":0.2564841026161451,"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."}}