{"id":"W1600046456","doi":"","title":"Off-Policy Temporal Difference Learning with Function Approximation","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":254,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Temporal difference learning; Computer science; Function approximation; Function (biology); Artificial intelligence; Reinforcement learning; 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":[0.0032947,0.001141442,0.001641894,0.0007350025,0.0005181968,0.001425255,0.003069015,0.002271652,0.007307505],"category_scores_gemma":[0.01263729,0.0006367684,0.0008568828,0.0008196895,0.001867261,0.002441896,0.002988291,0.003769537,0.001498401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001956615,"about_ca_system_score_gemma":0.002237915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003636187,"about_ca_topic_score_gemma":0.002314019,"domain_scores_codex":[0.9986171,0.0003709684,0.00007567472,0.0002993096,0.0004491298,0.0001878533],"domain_scores_gemma":[0.9960349,0.002621733,0.0002524039,0.000370947,0.000520805,0.0001991537],"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":[0.0003134864,0.000236206,0.001060862,0.0001587575,0.00005696307,0.0001128839,0.0001649289,0.6316692,0.002081516,0.1123398,0.004305748,0.2474997],"study_design_scores_gemma":[0.00001524244,0.00003364303,0.00002897855,0.000009603483,0.000002896188,0.00001835902,0.000003964853,0.9859473,0.000417484,0.01281674,0.0007013529,0.000004523283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003496256,0.0001500753,0.9932249,0.0001840198,0.00006489106,0.00006729941,0.00002771369,0.0004195545,0.002365196],"genre_scores_gemma":[0.4262032,0.0002563175,0.5633009,0.0007245957,0.0001176122,0.000512255,0.0002784972,0.0003407318,0.008266045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007307505,"threshold_uncertainty_score":0.02444601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01561973101356947,"score_gpt":0.2314765468665761,"score_spread":0.2158568158530067,"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."}}