{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001908588,0.001525642,0.002154395,0.0008684559,0.0006483495,0.001014572,0.001655518,0.001928767,0.004103673],"category_scores_gemma":[0.006495226,0.0007535406,0.001064927,0.000734428,0.001700238,0.001695697,0.002605689,0.00236344,0.0014017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001370274,"about_ca_system_score_gemma":0.002496356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003657576,"about_ca_topic_score_gemma":0.002390497,"domain_scores_codex":[0.9987186,0.0005085002,0.00005900891,0.000277922,0.0003284831,0.0001074082],"domain_scores_gemma":[0.9983582,0.0009181718,0.0001159372,0.0001591298,0.0003180388,0.0001305959],"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":[0.0000776829,0.00006451265,0.0003364474,0.000169715,0.00007603029,0.00009939625,0.00008530496,0.8274258,0.001876496,0.1091911,0.00391987,0.05667762],"study_design_scores_gemma":[0.00000802623,0.00002461605,0.00003454125,0.000006360034,0.000004905807,0.00001828929,0.000003748246,0.9780116,0.0003229431,0.02050024,0.00105786,0.000006845233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001519219,0.0001396573,0.9968306,0.0001171933,0.00003173537,0.00002272359,0.00001524271,0.000190627,0.001133028],"genre_scores_gemma":[0.3579765,0.0009036083,0.6280558,0.000713717,0.0001955586,0.0004247006,0.0003369395,0.0005439136,0.01084929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004103673,"threshold_uncertainty_score":0.01372814,"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."}}