{"id":"W2411727234","doi":"","title":"Online Relative Entropy Policy Search using Reproducing Kernel Hilbert Space Embeddings","year":2016,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reproducing kernel Hilbert space; Hilbert space; Computer science; Entropy (arrow of time); Kernel (algebra); Mathematics; Theoretical computer science; Pure mathematics; Physics","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":[0.004080823,0.001030388,0.003822234,0.001473688,0.00079538,0.002337958,0.001973213,0.003034559,0.005574155],"category_scores_gemma":[0.01563632,0.001143268,0.001227523,0.001291613,0.001807357,0.005065352,0.003497396,0.002943872,0.0008721332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001316506,"about_ca_system_score_gemma":0.002179405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002494999,"about_ca_topic_score_gemma":0.001809779,"domain_scores_codex":[0.9978504,0.001046259,0.0001408996,0.0003153392,0.0004499381,0.0001972808],"domain_scores_gemma":[0.9889867,0.008926229,0.0004677975,0.0006689948,0.000558146,0.0003920778],"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":[0.0005648447,0.0004218512,0.0008303804,0.0001961127,0.0001405079,0.0001242014,0.0001238856,0.8088478,0.001297466,0.08967202,0.002590573,0.09519029],"study_design_scores_gemma":[0.00002164273,0.00003616576,0.0000315995,0.000005301308,0.000006164762,0.00001008875,0.000005616395,0.988088,0.0001427458,0.01153375,0.0001126398,0.000006376633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02939042,0.0005372458,0.9665867,0.0005906295,0.0001126168,0.00005622832,0.00005242825,0.0005035626,0.002170109],"genre_scores_gemma":[0.8324967,0.0003520676,0.1619821,0.0002909985,0.0001747838,0.0001976245,0.0002220846,0.0002328242,0.004050846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005574155,"threshold_uncertainty_score":0.02158171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1072556492704581,"score_gpt":0.3733498218374874,"score_spread":0.2660941725670293,"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."}}