{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001513505,0.00012133,0.00009936544,0.0001461771,0.0001631823,0.0002100491,0.0003344572,0.00004377302,0.00003732549],"category_scores_gemma":[0.000051394,0.00009231205,0.00002308696,0.0005853257,0.00003022502,0.0005203834,0.0001031207,0.0001846576,0.0001131415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005544786,"about_ca_system_score_gemma":0.00006954476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006489439,"about_ca_topic_score_gemma":0.000006579305,"domain_scores_codex":[0.9989574,0.00005043814,0.0001620384,0.0002522212,0.0003323207,0.0002455905],"domain_scores_gemma":[0.9993996,0.00003939699,0.0001120166,0.0003083909,0.00007594762,0.0000646746],"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":[0.00002740299,0.0000318824,0.07366014,0.0000138534,0.00002018632,0.000006965558,0.000439335,0.700115,0.0003113858,0.08705508,0.00009836206,0.1382204],"study_design_scores_gemma":[0.0002902564,0.0003406899,0.02185859,0.00001466385,0.00000377003,0.00002140267,0.00004364315,0.9702744,0.00008383077,0.0003519406,0.006556002,0.0001607357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01558563,0.00000786569,0.9553232,0.0004910995,0.00007130956,0.0001127137,1.922036e-8,0.0004302774,0.02797789],"genre_scores_gemma":[0.9432571,0.00001317453,0.03908758,0.0002219266,0.00008110137,0.000009377155,0.000005918902,0.000008985148,0.01731485],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9276714,"threshold_uncertainty_score":0.3764376,"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."}}