{"id":"W4401413897","doi":"10.1109/icra57147.2024.10610017","title":"Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Reinforcement learning; Robot; Computer science; Domain (mathematical analysis); Randomization; Artificial intelligence; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.001558886,0.0002677066,0.0004011354,0.000444446,0.0001478848,0.0002907429,0.0008789343,0.0001104864,0.00004550807],"category_scores_gemma":[0.0004050131,0.0002454475,0.0001195374,0.0009621604,0.0000442908,0.0006168722,0.0003953032,0.0003372689,0.000005060403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002793583,"about_ca_system_score_gemma":0.0002301283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005233681,"about_ca_topic_score_gemma":0.00005109075,"domain_scores_codex":[0.9973543,0.0001269476,0.0009052762,0.0005551202,0.0005281763,0.0005301367],"domain_scores_gemma":[0.9985957,0.0004589692,0.0002728823,0.0004850594,0.000106506,0.00008090807],"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":[0.00003619813,0.0000150047,0.0001447914,0.0001867477,0.00002471185,0.000002991181,0.003187452,0.9588628,0.00236815,0.03126712,0.0007815732,0.003122443],"study_design_scores_gemma":[0.001946034,0.0001719577,0.00008742305,0.0002287189,0.00001209515,0.000001422196,0.00008682418,0.9905757,0.004259308,0.0005787855,0.001784825,0.0002669436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001436964,0.0002581674,0.9817514,0.000386519,0.0004287662,0.0009403551,9.786444e-7,0.0003899971,0.01440683],"genre_scores_gemma":[0.8393993,0.00004005453,0.1514439,0.00008537838,0.00005810178,0.00006506871,0.00004110254,0.00003741719,0.008829618],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8379624,"threshold_uncertainty_score":0.9999998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009420998089325656,"score_gpt":0.2612918408277262,"score_spread":0.2518708427384005,"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."}}