{"id":"W2115253045","doi":"","title":"Off-policy Learning with Options and Recognizers","year":2005,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; McGill University","funders":"","keywords":"Variance (accounting); Computer science; Convergence (economics); Function (biology); Temporal difference learning; Reinforcement learning; Sampling (signal processing); Filter (signal processing); Function approximation; State (computer science); Importance sampling; Artificial intelligence; Policy learning; Algorithm; Machine learning; Mathematical optimization; Mathematics; Statistics; Artificial neural network","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":[0.002459138,0.0006710609,0.00113215,0.0005971378,0.0003341996,0.001203527,0.002197055,0.001496236,0.002661106],"category_scores_gemma":[0.009931841,0.0005324236,0.0006099107,0.0005032591,0.00167852,0.002405459,0.001991589,0.002148078,0.0005040884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001197752,"about_ca_system_score_gemma":0.001276346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001942359,"about_ca_topic_score_gemma":0.001443673,"domain_scores_codex":[0.9987084,0.0003825876,0.00008652303,0.0002688091,0.0004368443,0.0001168885],"domain_scores_gemma":[0.9965228,0.002171317,0.0002860278,0.0005093619,0.0003659294,0.0001446171],"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":[0.0002815099,0.0002067446,0.001188256,0.00009420468,0.00005971277,0.000144612,0.0001813232,0.5694454,0.004880484,0.1262134,0.00140382,0.2959005],"study_design_scores_gemma":[0.00001195495,0.00003103623,0.00004314151,0.000005031087,0.000003615192,0.00001974492,0.00000428065,0.9863013,0.001048941,0.01208572,0.0004403154,0.000004922216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007782258,0.00005790996,0.9906855,0.00008848803,0.00002793589,0.00003426219,0.000009168648,0.0002673907,0.001046949],"genre_scores_gemma":[0.5298639,0.0001256404,0.4649906,0.0002893233,0.00006363437,0.0002433745,0.00008311288,0.0001454168,0.004194955],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002661106,"threshold_uncertainty_score":0.01300532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01260585407427968,"score_gpt":0.2424030683691066,"score_spread":0.2297972142948269,"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."}}