{"id":"W7052860977","doi":"","title":"A study in using temporal abstraction and function approximation in reinforcement learning /","year":2006,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Library and Archives Canada","funders":"","keywords":"Abstraction; Function (biology); Reinforcement learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.004027041,0.0005107491,0.0007110711,0.0003383245,0.000334674,0.001250764,0.001103157,0.0007047709,0.003456301],"category_scores_gemma":[0.01499235,0.0002941007,0.000668393,0.0005318867,0.001000539,0.002816684,0.0008868314,0.001788589,0.0002743179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00188677,"about_ca_system_score_gemma":0.001691822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01338166,"about_ca_topic_score_gemma":0.006466185,"domain_scores_codex":[0.9987118,0.0007724765,0.00005798324,0.0001853709,0.0001745795,0.0000977922],"domain_scores_gemma":[0.9905814,0.007832354,0.0003676295,0.0004947576,0.0004721854,0.0002516842],"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":[0.001656937,0.000926221,0.007839206,0.00035345,0.0002680795,0.0001133581,0.0007975814,0.4868386,0.006606881,0.09901182,0.001702313,0.3938856],"study_design_scores_gemma":[0.00006279271,0.0002873422,0.0006646732,0.00001991198,0.00003628878,0.00002675757,0.00006099512,0.9826421,0.00123604,0.01383784,0.001115205,0.00001008295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1930154,0.001488236,0.7854196,0.001487036,0.0001380847,0.0002052398,0.0000659017,0.0005163879,0.0176642],"genre_scores_gemma":[0.8809837,0.0005825225,0.1132447,0.0002172505,0.00004367082,0.0001433322,0.00004179839,0.00005215116,0.004690851],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01338166,"threshold_uncertainty_score":0.02660751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02157889925998559,"score_gpt":0.274453007014695,"score_spread":0.2528741077547094,"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."}}