{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006621967,0.001574373,0.00195134,0.000857376,0.0004621243,0.001603014,0.001275666,0.001666011,0.001935994],"category_scores_gemma":[0.02023606,0.0006558642,0.001136684,0.000735711,0.002319959,0.003784661,0.002019372,0.0026621,0.000269994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002303482,"about_ca_system_score_gemma":0.001935436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00287972,"about_ca_topic_score_gemma":0.001568357,"domain_scores_codex":[0.996752,0.001910793,0.0001792332,0.0004664554,0.0004353182,0.0002562382],"domain_scores_gemma":[0.9841248,0.013647,0.0008373839,0.0003686949,0.0007030291,0.0003189677],"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":[0.0000812123,0.00004326233,0.000431341,0.000106195,0.00003592149,0.00004248176,0.00007196165,0.9139067,0.0004033491,0.06908907,0.0002329139,0.01555559],"study_design_scores_gemma":[0.000006136187,0.00002696323,0.00006296959,0.00001114058,0.000007197023,0.000008489058,0.000006295256,0.9781584,0.0001532818,0.02141816,0.0001333044,0.000007716471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01085991,0.0004922769,0.9874126,0.0002435015,0.00002584466,0.00003199349,0.0000247512,0.00008606649,0.0008231121],"genre_scores_gemma":[0.8121806,0.001155874,0.1827454,0.0002044456,0.00009069709,0.0002907737,0.0001606951,0.0001534144,0.00301804],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006621967,"threshold_uncertainty_score":0.03502077,"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."}}