{"id":"W1556824961","doi":"10.1007/3-540-45622-8_16","title":"Learning Options in Reinforcement Learning","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Psychology; Artificial intelligence","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001448459,0.0006915959,0.0006557687,0.001862354,0.0004730661,0.0008107211,0.003371776,0.0004224241,0.0001405219],"category_scores_gemma":[0.0003523065,0.0007209074,0.0001421735,0.001159943,0.0004966671,0.0009313479,0.001998236,0.003139857,0.0002779543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008368075,"about_ca_system_score_gemma":0.0003227981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003021724,"about_ca_topic_score_gemma":0.00001797927,"domain_scores_codex":[0.994575,0.00009721199,0.0009717394,0.00166236,0.001544706,0.001148935],"domain_scores_gemma":[0.9972336,0.0005613707,0.0005350243,0.001248701,0.0002109309,0.0002104324],"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":[0.000001800288,0.000009474928,0.0001944999,0.00002449112,0.000007078985,0.00008053609,0.001000061,0.8959591,0.00002666361,0.01240253,0.000006909607,0.0902869],"study_design_scores_gemma":[0.0003435532,0.000415549,0.0001366579,0.0005290617,0.000005770522,0.00004033422,5.469884e-7,0.9873369,0.00006838211,0.004950698,0.005414336,0.0007581717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003850032,0.0001999942,0.974399,0.0003995299,0.001060396,0.0004346616,1.768159e-7,0.0003119211,0.02315585],"genre_scores_gemma":[0.6001106,0.0007126376,0.3726501,0.001051521,0.0006231231,0.00003717071,0.0000207032,0.000134026,0.0246601],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6017488,"threshold_uncertainty_score":0.9995242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02108976112327637,"score_gpt":0.2445734416842048,"score_spread":0.2234836805609284,"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."}}