{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001795468,0.00009287867,0.0001281759,0.0005990842,0.0002725683,0.0002002976,0.0005048928,0.00005984934,0.00008719236],"category_scores_gemma":[0.0004803068,0.00009155396,0.00003942791,0.001015105,0.00006737973,0.0008712418,0.000208319,0.0004367151,0.0001047277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005640941,"about_ca_system_score_gemma":0.0001910033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004123539,"about_ca_topic_score_gemma":0.000230164,"domain_scores_codex":[0.9977658,0.000321806,0.0004344844,0.0002619718,0.0008473764,0.0003685946],"domain_scores_gemma":[0.9986761,0.0001499368,0.00004510645,0.0003815484,0.000675984,0.00007130287],"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":[0.00001065656,0.00003482899,0.00141161,0.000008560532,0.000007176196,7.922054e-7,0.001046489,0.9596584,0.0006477443,0.0179498,0.0002057346,0.01901819],"study_design_scores_gemma":[0.0001889004,0.0003406269,0.007907618,0.00003693445,8.063308e-7,6.671843e-7,0.000214714,0.9867536,0.002050462,0.00006248661,0.002354988,0.00008817683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05995004,0.00007519144,0.9328964,0.003314867,0.00005075815,0.0002850705,2.269717e-7,0.00004330525,0.003384158],"genre_scores_gemma":[0.9845845,0.0001614608,0.01089541,0.0001073689,0.00004718338,0.00004593613,0.00001631987,0.000007037598,0.004134838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9246344,"threshold_uncertainty_score":0.3733462,"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."}}