{"id":"W2407045295","doi":"10.13140/2.1.3356.8002","title":"Efficient Abstraction Selection in Reinforcement Learning --- Extended Abstract","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Abstraction; Reinforcement learning; Computer science; Markov decision process; Selection (genetic algorithm); Set (abstract data type); Artificial intelligence; State (computer science); Markov process; Machine learning; Theoretical computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000367797,0.0001585324,0.0001305419,0.0002632309,0.0001297378,0.0002740074,0.0003446869,0.00008250534,0.0006946368],"category_scores_gemma":[0.00007685857,0.0001494359,0.000040871,0.0004588119,0.00001779244,0.0004832894,0.0001081448,0.000414121,0.001255641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002214756,"about_ca_system_score_gemma":0.00004566469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004120972,"about_ca_topic_score_gemma":0.000008702405,"domain_scores_codex":[0.9983565,0.00003524236,0.0004347003,0.0003376355,0.0004251058,0.0004107886],"domain_scores_gemma":[0.9993588,0.00007842756,0.0001710742,0.0002061903,0.0001005108,0.00008500492],"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":[0.000001822457,0.00002665536,0.0006291227,0.000007695493,0.000005222472,0.000001660898,0.0001953151,0.9853791,0.003957551,0.002927827,0.0001492926,0.006718711],"study_design_scores_gemma":[0.0002506776,0.0001069293,0.09019968,0.00001576905,0.000001358091,0.000006811123,0.00005939143,0.9074584,0.001172324,0.00007127957,0.0004931538,0.0001642655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09150583,0.000005512936,0.8718867,0.0002332317,0.0002111275,0.000350722,8.16699e-9,0.0003346849,0.03547214],"genre_scores_gemma":[0.9852377,0.000005195507,0.0103888,0.00009645941,0.00003390215,0.00004028299,0.000001828325,0.00001009049,0.004185783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8937318,"threshold_uncertainty_score":0.999522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01256500116340309,"score_gpt":0.2434278053132065,"score_spread":0.2308628041498034,"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."}}