{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003167422,0.0001462463,0.0001386325,0.0001304069,0.0003020079,0.0003277692,0.0001577913,0.00005818046,0.00001730117],"category_scores_gemma":[0.00003346111,0.0001375079,0.0000471305,0.0002063135,0.00005133558,0.0004999363,0.0001014569,0.0001054299,0.00000830102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007394009,"about_ca_system_score_gemma":0.00002413159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002481319,"about_ca_topic_score_gemma":0.000002966593,"domain_scores_codex":[0.9988219,0.00002864943,0.0003235354,0.0002978648,0.0002204752,0.0003076362],"domain_scores_gemma":[0.9994066,0.00008116142,0.0001813806,0.0002097765,0.00007789013,0.00004314812],"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":[0.000006091732,0.00001052799,0.001597743,0.0001376116,0.00002354845,5.533726e-7,0.00009775284,0.7013717,0.0002401071,0.08298004,0.00006200455,0.2134724],"study_design_scores_gemma":[0.0004284417,0.0002253922,0.0008428014,0.00002351553,0.00001904559,0.00001469749,0.00008722395,0.9951972,0.0001625619,0.000848104,0.001983804,0.00016722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00663028,0.00002047094,0.990248,0.000141283,0.0002281023,0.0005401471,7.069852e-8,0.0006070948,0.001584596],"genre_scores_gemma":[0.6213385,0.000003946006,0.3770183,0.00003420488,0.00002467402,0.00007104449,0.00001504772,0.00001082716,0.001483518],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6147082,"threshold_uncertainty_score":0.5607411,"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."}}