{"id":"W4399019070","doi":"10.1016/j.eswa.2024.124310","title":"Bridging the simulation-to-real gap of depth images for deep reinforcement learning","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Encoder; Bridging (networking); Bridge (graph theory); Perception; Virtual reality; Machine learning; Deep learning; Computer vision","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":[],"consensus_categories":[],"category_scores_codex":[0.0003427074,0.0001481958,0.0001620464,0.000126644,0.0003333981,0.0003221376,0.0006135462,0.00003593823,0.000003318013],"category_scores_gemma":[0.00004436865,0.0001022276,0.0000595343,0.0005471752,0.0000419154,0.000232107,0.0001079175,0.0001143977,0.00004062297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008074779,"about_ca_system_score_gemma":0.000080009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001243796,"about_ca_topic_score_gemma":0.000003293905,"domain_scores_codex":[0.9986287,0.00004041723,0.0003874996,0.0003365624,0.0003535327,0.0002532832],"domain_scores_gemma":[0.9984215,0.0005607377,0.0001426483,0.0006136386,0.000187033,0.00007444128],"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":[0.000003168279,0.000005003474,0.00009592267,0.00007208832,0.00003677531,3.324221e-7,0.001580742,0.9514202,0.0003200308,0.04297519,0.0006744922,0.002816032],"study_design_scores_gemma":[0.0000873264,0.00008562313,0.00005423594,0.000121005,0.000009617309,0.000004652775,0.0002382525,0.9482096,0.0002336958,0.00001689257,0.05081067,0.0001284726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003747489,0.0003246079,0.9934549,0.0007279476,0.0001474856,0.001771259,7.592361e-7,0.0002830974,0.003252521],"genre_scores_gemma":[0.9752614,0.00001908092,0.02017295,0.00006463689,0.0002284108,0.002062449,0.00001187692,0.00002577505,0.002153439],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9752239,"threshold_uncertainty_score":0.4168721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02510632329526433,"score_gpt":0.3069211344319391,"score_spread":0.2818148111366747,"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."}}