{"id":"W1998172110","doi":"10.1007/s10479-005-5732-z","title":"Basis Function Adaptation in Temporal Difference Reinforcement Learning","year":2005,"lang":"en","type":"article","venue":"Annals of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Markov decision process; Bellman equation; Temporal difference learning; Basis function; Function approximation; Mathematical optimization; Basis (linear algebra); Computer science; Theory of computation; Q-learning; Convergence (economics); Markov process; Mathematics; Artificial intelligence; Algorithm; 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":[0.002156965,0.0004628069,0.001036601,0.0002996183,0.0003106451,0.0008035448,0.001197531,0.001277319,0.002481228],"category_scores_gemma":[0.007963539,0.0004517107,0.0003984519,0.0004819992,0.001156757,0.001410461,0.00100418,0.001793241,0.0002447949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007637889,"about_ca_system_score_gemma":0.0008450272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003736595,"about_ca_topic_score_gemma":0.002076547,"domain_scores_codex":[0.9995046,0.0002457621,0.00002453999,0.00007739335,0.00009781486,0.00004990099],"domain_scores_gemma":[0.9972149,0.002173254,0.0001034829,0.0001162979,0.0003095017,0.00008235032],"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":[0.0001493416,0.00009672557,0.000505315,0.00007805336,0.00005136018,0.00004578877,0.0000649386,0.8295184,0.001598138,0.1031067,0.001262192,0.06352302],"study_design_scores_gemma":[0.000007551465,0.00001214087,0.00003912542,0.000002308833,0.000003143494,0.000004201376,0.000001976132,0.9855955,0.0001063757,0.0140952,0.0001297879,0.000002753273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02904971,0.0006060337,0.9670018,0.0003614545,0.0001261782,0.00002196214,0.00002153561,0.00009687037,0.002714414],"genre_scores_gemma":[0.8872939,0.0006511523,0.1028082,0.0001924876,0.0001174554,0.0001765247,0.00006666827,0.00008739467,0.008606263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003736595,"threshold_uncertainty_score":0.0114072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2255396635006515,"score_gpt":0.4118928531180281,"score_spread":0.1863531896173766,"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."}}