{"id":"W2162926979","doi":"10.1109/cdc.2009.5400662","title":"Arbitrarily modulated Markov decision processes","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Transition (genetics); Computer science; Markov chain; Markov process; Markov model; Partially observable Markov decision process; Decision theory; Artificial intelligence; Mathematical optimization; Machine learning; Algorithm; Mathematics; Statistics","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":[0.001767126,0.00115199,0.001346689,0.0005171053,0.0006203085,0.001662534,0.001846654,0.00216357,0.003473134],"category_scores_gemma":[0.009189716,0.0004896552,0.0009899989,0.0008765295,0.002156784,0.001861128,0.001877869,0.00279775,0.0007179853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001312605,"about_ca_system_score_gemma":0.0009657545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00263505,"about_ca_topic_score_gemma":0.001635665,"domain_scores_codex":[0.9983017,0.0006949944,0.00006606569,0.0003965015,0.0003056017,0.0002350895],"domain_scores_gemma":[0.9956416,0.002883949,0.0006225884,0.0002975082,0.000258419,0.0002958686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001715568,0.00009079758,0.00124665,0.0001005257,0.00006965538,0.0004067541,0.0001537018,0.5917566,0.002114245,0.3876564,0.001081154,0.01515188],"study_design_scores_gemma":[0.00002826921,0.00003364796,0.0001022838,0.000007815595,0.00001254483,0.00002632162,0.000007028614,0.9126756,0.0002506531,0.08611479,0.0007310506,0.00001008063],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03955874,0.0005403887,0.9526248,0.0008961754,0.0001761097,0.00009816838,0.0001481768,0.000193494,0.005764042],"genre_scores_gemma":[0.9095476,0.0007236749,0.08226997,0.0003870593,0.0002279689,0.0002382972,0.0001651791,0.00003197206,0.006408223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003473134,"threshold_uncertainty_score":0.01161879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009695192704821434,"score_gpt":0.241276952183283,"score_spread":0.2315817594784616,"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."}}