{"id":"W4392943351","doi":"10.1109/icmla58977.2023.00048","title":"Preferential Proximal Policy Optimization","year":2023,"lang":"en","type":"article","venue":"","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science","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":[0.002198412,0.001275388,0.002055369,0.0007760533,0.0005557463,0.00122673,0.001489258,0.00163213,0.005531644],"category_scores_gemma":[0.006774989,0.0007073932,0.0008076844,0.000872841,0.001316757,0.001332955,0.001886275,0.002017702,0.001184356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009824487,"about_ca_system_score_gemma":0.002600692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003774431,"about_ca_topic_score_gemma":0.003324533,"domain_scores_codex":[0.9987558,0.0005404082,0.00005701031,0.0002275815,0.000265715,0.0001534502],"domain_scores_gemma":[0.9977138,0.001441003,0.0001664637,0.0001905361,0.0003595966,0.0001286521],"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":[0.0001336372,0.00007630738,0.0007591652,0.000134356,0.00006767762,0.0000789641,0.00006277377,0.9065877,0.0008723724,0.0259632,0.003553635,0.06171021],"study_design_scores_gemma":[0.00001455533,0.0000426833,0.00006361261,0.00001232284,0.000009759301,0.00002252873,0.000007322077,0.9890577,0.0003259935,0.009463114,0.0009743892,0.000006007636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005373366,0.0002938239,0.9905819,0.0001814681,0.00005822097,0.00005628189,0.00004170987,0.0003887727,0.003024414],"genre_scores_gemma":[0.6149022,0.0006712679,0.3729263,0.0006353551,0.0001382703,0.0003837906,0.0003264233,0.000323734,0.009692634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005531644,"threshold_uncertainty_score":0.01850516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1161325673453281,"score_gpt":0.4136075758443717,"score_spread":0.2974750084990436,"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."}}