{"id":"W1491129446","doi":"10.1007/978-3-540-39857-8_29","title":"Using MDP Characteristics to Guide Exploration in Reinforcement Learning","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Artificial intelligence; Bellman equation; Machine learning; State space; Computation; Focus (optics); Variance (accounting); Markov process; Mathematical optimization; Algorithm","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":[0.001509975,0.0006071806,0.0006157045,0.00154985,0.0002823457,0.0007852214,0.002343468,0.0003076709,0.00002350387],"category_scores_gemma":[0.0004339155,0.0006455745,0.00008186902,0.001056166,0.0002068271,0.001107414,0.001300649,0.001163476,0.00007718629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001268723,"about_ca_system_score_gemma":0.0005558954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003379561,"about_ca_topic_score_gemma":0.00002069401,"domain_scores_codex":[0.9951622,0.00007544892,0.001111115,0.001408769,0.001334554,0.0009079277],"domain_scores_gemma":[0.9974659,0.0002505073,0.0005278275,0.001232935,0.0003025373,0.0002202706],"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":[0.000003277695,0.000005546193,0.0001089231,0.00002409247,0.000004556618,0.00005322036,0.001283537,0.9507159,0.0002061319,0.004758101,0.00001134303,0.04282537],"study_design_scores_gemma":[0.0002142651,0.0002476955,0.00004450278,0.0005766943,0.000005529008,0.00002416045,7.433201e-7,0.9891039,0.0005019771,0.002747714,0.005815068,0.0007177697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008463082,0.00003790695,0.9933434,0.000427379,0.001731276,0.0006162493,4.201741e-7,0.0001228171,0.003635918],"genre_scores_gemma":[0.1126829,0.00007686661,0.8799276,0.003885174,0.0004381693,0.00002121786,0.0000168229,0.00009219153,0.0028591],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1134158,"threshold_uncertainty_score":0.9995996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04465666491859917,"score_gpt":0.2856795728748343,"score_spread":0.2410229079562351,"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."}}