{"id":"W2783447922","doi":"10.1109/allerton.2017.8262843","title":"Transition-based versus state-based reward functions for MDPs with Value-at-Risk","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Markov decision process; Reinforcement learning; Markov process; Function (biology); Bellman equation; Action (physics); Transformation (genetics); Computer science; Markov chain; Mathematical optimization; State (computer science); Markov model; Mathematics; Artificial intelligence; Machine learning; Statistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.00029729,0.0001758594,0.0001550289,0.00008678412,0.001271335,0.0004120767,0.0008126554,0.00005367614,0.00005691513],"category_scores_gemma":[0.0001182242,0.000144397,0.0001051825,0.00009436767,0.0001158366,0.0003848634,0.00004904264,0.000129401,0.00009248732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001132506,"about_ca_system_score_gemma":0.0002382608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001433179,"about_ca_topic_score_gemma":0.0001070421,"domain_scores_codex":[0.9986494,0.00004356781,0.0001983336,0.0003944286,0.0003639605,0.0003502635],"domain_scores_gemma":[0.9978032,0.0003774638,0.0002266764,0.001297217,0.0001713803,0.0001240635],"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":[0.0003275195,0.00002646882,0.0007393612,0.0000174307,0.00003588131,0.000003050876,0.00009780949,0.9951248,0.00002742591,0.001216994,0.001420329,0.0009629745],"study_design_scores_gemma":[0.004433372,0.001022019,0.001559291,0.00002161211,0.00004356113,5.714902e-7,0.00001507317,0.9847559,0.001425601,0.00006583086,0.006408793,0.000248352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004714645,0.000003499497,0.9882697,0.00199846,0.0005518816,0.0004084704,0.0000143141,0.0002807349,0.003758312],"genre_scores_gemma":[0.7803119,0.000001590818,0.2154935,0.0004745182,0.00005370679,0.00008227329,0.00003448948,0.0000255888,0.003522436],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7755972,"threshold_uncertainty_score":0.9778213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02514385116644622,"score_gpt":0.2594024720053066,"score_spread":0.2342586208388604,"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."}}