{"id":"W359568995","doi":"","title":"A convergent O ( n ) algorithm for off-policy temporal-difference learning with linear function approximation","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Temporal difference learning; Markov decision process; Algorithm; Stochastic approximation; Function (biology); Reinforcement learning; Stochastic gradient descent; Markov process; Mathematics; Quadratic equation; Approximation algorithm; Norm (philosophy); Computer science; Function approximation; Mathematical optimization; Applied mathematics; Artificial intelligence; 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":[0.001867837,0.001108586,0.001220631,0.0006826366,0.0006233912,0.001051008,0.002579343,0.001722472,0.008051493],"category_scores_gemma":[0.008128007,0.000618944,0.0007617791,0.0006622829,0.001187645,0.001799745,0.002431361,0.003345339,0.003095479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001715408,"about_ca_system_score_gemma":0.002252647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004988086,"about_ca_topic_score_gemma":0.004152969,"domain_scores_codex":[0.9988976,0.0002188131,0.00007113923,0.0002796619,0.0004119797,0.0001208145],"domain_scores_gemma":[0.998046,0.001050529,0.000130837,0.0002318398,0.0004217121,0.0001189539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003274444,0.0001960177,0.0007341583,0.0001585166,0.0000498368,0.0001263378,0.0001638461,0.4185304,0.00530529,0.0661085,0.006849732,0.5014498],"study_design_scores_gemma":[0.00002460053,0.00003043525,0.00003836428,0.000008624143,0.000003512223,0.00002738759,0.000006736061,0.9873511,0.0007685645,0.01048602,0.001248077,0.000006507244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001509989,0.00009158822,0.9967186,0.000102977,0.00004331573,0.00004912211,0.00001559557,0.0004685019,0.001000389],"genre_scores_gemma":[0.1220626,0.0001411467,0.8715371,0.0003112572,0.00007819555,0.0004255668,0.0002074403,0.0002847689,0.004951846],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008051493,"threshold_uncertainty_score":0.02693492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02640782854945645,"score_gpt":0.2470170740798348,"score_spread":0.2206092455303784,"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."}}