{"id":"W3046558900","doi":"10.5539/cis.v13n3p93","title":"Riemannian Proximal Policy Optimization","year":2020,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Mathematical optimization; Markov decision process; Optimization problem; Convergence (economics); Upper and lower bounds; Space (punctuation); Process (computing); Applied mathematics; Mathematics; Markov process; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002920184,0.00007960228,0.0000748496,0.0002290576,0.0003187998,0.0009605429,0.0005668282,0.00002110505,0.000007799642],"category_scores_gemma":[0.00009792751,0.00007274748,0.00001679945,0.001415304,0.000141826,0.01241225,0.0003162166,0.00007662654,0.00007089454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002212532,"about_ca_system_score_gemma":0.0001904869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002552712,"about_ca_topic_score_gemma":2.999867e-8,"domain_scores_codex":[0.9990405,0.00001710137,0.0002169655,0.0001801437,0.0003533103,0.0001919874],"domain_scores_gemma":[0.9993387,0.00001742675,0.00009604368,0.0001495273,0.000175317,0.0002229399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006159785,0.00001037179,0.0002448611,0.00002750877,0.000002827309,0.000001019923,0.0178046,0.1824618,0.00007940604,0.4199703,0.0005823337,0.3788089],"study_design_scores_gemma":[0.0001968708,0.00006162716,0.002332669,0.000004471477,4.639157e-7,0.000008323929,0.00004378253,0.9729729,0.00007052236,0.00007226683,0.0241418,0.00009426957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007355297,0.000006996733,0.9845064,0.006056692,0.0001209843,0.0001052954,5.307761e-7,0.0001697958,0.008297746],"genre_scores_gemma":[0.5763221,0.00001708314,0.4082566,0.01525243,0.0001302238,0.00000421153,0.000003500995,0.000002344694,0.00001154076],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7905112,"threshold_uncertainty_score":0.9262538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0155222719762258,"score_gpt":0.2423792124558375,"score_spread":0.2268569404796117,"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."}}