{"id":"W4413319271","doi":"10.1109/arso64737.2025.11124980","title":"Deep Reinforcement Learning for Robotic Grasping: Insights into Learning from Raw Visual Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Raw data; Deep learning; Human–computer interaction; Robot learning; Computer vision; Robot; Mobile robot","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001342303,0.0002116377,0.0002510379,0.0002070233,0.0003237931,0.0001415712,0.0003178886,0.0001097011,0.0002296428],"category_scores_gemma":[0.0002663587,0.0002166558,0.00005769898,0.0002652181,0.0000183157,0.0003465055,0.0001976685,0.0004196641,0.00007905162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009131421,"about_ca_system_score_gemma":0.00002453555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001278911,"about_ca_topic_score_gemma":0.00009716084,"domain_scores_codex":[0.9987664,0.00005025779,0.0003795142,0.0003555116,0.0001596108,0.0002887566],"domain_scores_gemma":[0.9992711,0.0002286412,0.00005293157,0.000327709,0.00004685876,0.00007274683],"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":[0.00001018714,0.000006827738,0.001078318,0.00006269873,0.00009351927,0.000001088226,0.000557625,0.9927375,0.001250752,0.001422665,0.0004023574,0.002376469],"study_design_scores_gemma":[0.0005377352,0.00004000633,0.001242663,0.00007224788,0.00004225723,2.048189e-7,0.0005564675,0.9904451,0.0004492358,0.0001971796,0.006172542,0.0002443172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002010054,0.0004940246,0.9904615,0.00008144726,0.0004587176,0.0002498073,1.085639e-9,0.0006310462,0.005613455],"genre_scores_gemma":[0.9946057,0.00005396548,0.001562412,0.0001120923,0.0001303834,0.00002389641,0.0004881512,0.00004298871,0.002980431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9925956,"threshold_uncertainty_score":0.8834966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03555892906706197,"score_gpt":0.2869290723871008,"score_spread":0.2513701433200388,"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."}}