{"id":"W150352456","doi":"10.5072/zenodo.49098","title":"Learning by Automatic Option Discovery from Conditionally Terminating Sequences","year":2006,"lang":"en","type":"article","venue":"OpenMETU (Middle East Technical University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Normalization property; Computer science; Reinforcement learning; Tree (set theory); Tree structure; Artificial intelligence; Machine learning; Theoretical computer science; Data structure; Programming language; Mathematics","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":[0.002062082,0.0006923592,0.0009369775,0.0009362445,0.0004895714,0.0008371355,0.001960789,0.000952708,0.002155606],"category_scores_gemma":[0.01191236,0.0006413033,0.0007803452,0.0006763435,0.001253373,0.003356084,0.001581281,0.002121403,0.0004738315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006104797,"about_ca_system_score_gemma":0.001609725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001529393,"about_ca_topic_score_gemma":0.002695374,"domain_scores_codex":[0.9985285,0.0005436341,0.00009584856,0.0003312117,0.0003774836,0.0001234313],"domain_scores_gemma":[0.9913867,0.006466138,0.0006326285,0.0006794145,0.0005575967,0.000277608],"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":[0.001220204,0.0003774842,0.01062843,0.0003993767,0.0001488205,0.0006829328,0.0006596086,0.4087061,0.01937685,0.07966899,0.003820266,0.4743108],"study_design_scores_gemma":[0.00003681439,0.00007349419,0.0004418458,0.00002743971,0.00001561274,0.00008857487,0.00002403948,0.941896,0.00503864,0.05136786,0.0009646516,0.0000249932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05176372,0.0001390906,0.9451369,0.0001623537,0.00002109468,0.00005646641,0.0001493341,0.001578603,0.0009923815],"genre_scores_gemma":[0.6673023,0.0001239139,0.3304414,0.0001078786,0.00002720158,0.0001579009,0.0006189168,0.0001409301,0.001079646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002155606,"threshold_uncertainty_score":0.01090544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296326288476426,"score_gpt":0.195086123863933,"score_spread":0.1821228609791688,"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."}}