{"id":"W3097732461","doi":"10.48550/arxiv.2011.02565","title":"Diversity-Enriched Option-Critic","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Diversity (politics); Political science; Law","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0002006389,0.0003701769,0.0003790039,0.0002470369,0.0007474883,0.0001848674,0.003624486,0.0003017292,0.00004655113],"category_scores_gemma":[0.0001143228,0.0004786989,0.0002748251,0.0007171641,0.0001186918,0.0005332265,0.01895437,0.001076716,0.0004692351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000302107,"about_ca_system_score_gemma":0.0001862387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001152018,"about_ca_topic_score_gemma":0.000004413684,"domain_scores_codex":[0.9977147,0.0001797828,0.0002223738,0.001234396,0.0002095426,0.00043918],"domain_scores_gemma":[0.9977725,0.0001461455,0.0002542038,0.00133776,0.0001915368,0.0002979242],"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":[0.00000771249,0.00002092307,0.001934531,0.00007074173,0.000076793,0.0003383507,0.0005231191,0.7850764,0.00001392718,0.2115496,0.000337961,0.0000499364],"study_design_scores_gemma":[0.000397885,0.00006438467,0.001596785,0.00004645956,0.00008978425,0.000003135925,0.00007135291,0.9696517,0.00001689869,0.02685449,0.0006795214,0.0005276158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01827444,0.00002709189,0.9756382,0.0004992707,0.0009317331,0.0002710822,0.000004174575,0.0006316476,0.003722366],"genre_scores_gemma":[0.9923994,0.0001122043,0.004595284,0.0003821908,0.0001023069,4.560273e-7,0.00002357244,0.00001980636,0.002364775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.974125,"threshold_uncertainty_score":0.9997665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1188464807474624,"score_gpt":0.1945581158372311,"score_spread":0.07571163508976872,"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."}}