{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003330419,0.0002276933,0.0002046415,0.0001633874,0.0001292004,0.0004945613,0.0009886603,0.00005276704,0.0001773677],"category_scores_gemma":[0.0002251644,0.0001937198,0.00004359488,0.0001364179,0.0000549234,0.000477913,0.0003953949,0.0005431382,0.00007747731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004696855,"about_ca_system_score_gemma":0.00007210694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001496113,"about_ca_topic_score_gemma":0.00002425812,"domain_scores_codex":[0.9982998,0.000119027,0.0002531566,0.0004691745,0.0005884228,0.0002704178],"domain_scores_gemma":[0.9990155,0.0001458243,0.0002095019,0.0003118852,0.0001628502,0.0001544155],"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":[0.0001045232,0.00002605205,0.02129933,0.00004223515,0.0001170243,0.00002630632,0.001338486,0.3001727,0.000511555,0.4652646,0.0002074405,0.2108897],"study_design_scores_gemma":[0.0005625435,0.0007122847,0.001806736,0.0002505214,0.000007570677,0.00003886014,0.00002873256,0.9799035,0.000114495,0.0008080657,0.01550436,0.0002623498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005802064,0.00003945333,0.9613203,0.003180261,0.0002738818,0.0001015089,6.267881e-7,0.0001868754,0.02909502],"genre_scores_gemma":[0.9646347,0.00007349564,0.02952764,0.0005087558,0.00009552104,0.000008056833,0.000004363942,0.00001789247,0.005129643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9588326,"threshold_uncertainty_score":0.7899665,"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."}}