{"id":"W2011233848","doi":"10.1145/1143844.1143901","title":"Automatic basis function construction for approximate dynamic programming and reinforcement learning","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bellman equation; Markov decision process; Reinforcement learning; Computer science; Basis (linear algebra); Function approximation; Dynamic programming; Curse of dimensionality; Basis function; Mathematical optimization; State space; Temporal difference learning; Markov process; Dimensionality reduction; Q-learning; Function (biology); Space (punctuation); Artificial intelligence; Algorithm; Mathematics; 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":[0.002072582,0.0007558373,0.001500033,0.0008795962,0.0005583897,0.0009049407,0.001462673,0.001387208,0.002191551],"category_scores_gemma":[0.007400156,0.0006413195,0.0008307231,0.0007980954,0.0009992112,0.00160749,0.001556635,0.002237096,0.000841505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007694737,"about_ca_system_score_gemma":0.001032389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002143878,"about_ca_topic_score_gemma":0.001910257,"domain_scores_codex":[0.998953,0.000455419,0.00004715156,0.000139261,0.0003253942,0.00007983958],"domain_scores_gemma":[0.9979037,0.001176191,0.0001447868,0.0003154153,0.000389514,0.00007047344],"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":[0.00006899658,0.0001150263,0.0005144865,0.0001170849,0.00004535867,0.00006251086,0.0001120284,0.6976379,0.004512556,0.1034289,0.001401951,0.1919833],"study_design_scores_gemma":[0.000003640242,0.000009327377,0.00001384044,0.000003508206,0.000001371911,0.000005116886,0.000002033257,0.9867373,0.0004822041,0.01246651,0.0002718017,0.000003310081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002335824,0.00004467862,0.9971104,0.0000330998,0.00001098602,0.00001140961,0.000007413537,0.0001383746,0.0003079305],"genre_scores_gemma":[0.2030215,0.0001858727,0.7945531,0.00007054793,0.00004267281,0.0003371348,0.000122915,0.0002294353,0.001436725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002191551,"threshold_uncertainty_score":0.010961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007772714293839559,"score_gpt":0.2228768719720251,"score_spread":0.2151041576781855,"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."}}