{"id":"W3185807839","doi":"10.1109/tie.2021.3099234","title":"Reinforcement Learning With Constrained Uncertain Reward Function Through Particle Filtering","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Noise (video); Probabilistic logic; Process (computing); Computer science; Filter (signal processing); Particle filter; Artificial intelligence; Function (biology); Reinforcement; Quality (philosophy); Machine learning; Engineering; Computer vision","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000125712,0.0002071777,0.0002210665,0.00004572307,0.0002327616,0.00007928798,0.00006142622,0.000179033,0.0002542337],"category_scores_gemma":[0.000008063814,0.0002072838,0.00009127151,0.0004451921,0.00002909743,0.0001786089,5.937898e-7,0.0008001546,0.00003918221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003247563,"about_ca_system_score_gemma":0.0001635153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003212558,"about_ca_topic_score_gemma":0.0001307528,"domain_scores_codex":[0.9986873,0.00007664191,0.0003102553,0.0002344422,0.0002479951,0.0004433684],"domain_scores_gemma":[0.9995535,0.00006015223,0.00004332231,0.0002009705,0.00006000109,0.00008207514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002498642,0.00002616956,0.000002884223,0.0000120765,0.0001930615,0.00001029866,0.0001279882,0.9578105,0.02442624,0.0001805671,0.00008845028,0.01687191],"study_design_scores_gemma":[0.006282042,0.001794256,0.000002478514,0.0001466808,0.0002028998,0.0001316308,0.0009250425,0.4334335,0.4709601,0.00005982484,0.08540191,0.0006596412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07412917,0.0001541664,0.9210572,0.0001524211,0.001213543,0.0002935382,0.000004466128,0.0006736775,0.002321864],"genre_scores_gemma":[0.9982458,0.00008450974,0.00007221477,0.00006203139,0.0001559174,0.00009582505,0.000006566408,0.00004112307,0.001236003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9241166,"threshold_uncertainty_score":0.8452789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02347443230118521,"score_gpt":0.2229018177853744,"score_spread":0.1994273854841892,"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."}}