{"id":"W1460549585","doi":"10.1007/978-3-642-29946-9_13","title":"Regularized Least Squares Temporal Difference Learning with Nested ℓ2 and ℓ1 Penalization","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Overfitting; Computer science; Regularization (linguistics); Reinforcement learning; Solver; Mathematical optimization; Algorithm; Artificial intelligence; Applied mathematics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000500311,0.000621426,0.0005685614,0.0007141951,0.0004570105,0.0006059611,0.001353839,0.000272579,0.00001647501],"category_scores_gemma":[0.000135681,0.000523166,0.00005592164,0.0007919132,0.0008962433,0.001190208,0.0009144356,0.0008218595,0.00001007604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002348457,"about_ca_system_score_gemma":0.0003438608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002490928,"about_ca_topic_score_gemma":0.00005118966,"domain_scores_codex":[0.9963462,0.00009152969,0.0004417443,0.001509959,0.0009508486,0.0006597434],"domain_scores_gemma":[0.9976014,0.0003349687,0.0004911665,0.0008353918,0.0004877658,0.0002492943],"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":[0.00003655717,0.00005804892,0.003363698,0.00007093439,0.00002317369,0.00006951558,0.002082189,0.2196853,0.0003960951,0.0122853,0.000001437359,0.7619277],"study_design_scores_gemma":[0.0007643224,0.0002591868,0.0026638,0.0004287779,0.00001457355,0.0001969676,0.000001065646,0.9848639,0.0004757241,0.00915842,0.0002893813,0.0008838756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001905967,0.0005136618,0.9974788,0.0002148784,0.0004240009,0.000518818,0.000002221075,0.0002674751,0.0003895712],"genre_scores_gemma":[0.1542567,0.00008283046,0.8442907,0.0002901345,0.0002235352,0.00001626101,0.00001977475,0.00005862165,0.0007614775],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7651786,"threshold_uncertainty_score":0.999722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01232845308421654,"score_gpt":0.2322221378745569,"score_spread":0.2198936847903404,"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."}}