{"id":"W4415014469","doi":"10.1016/j.asoc.2025.114024","title":"Transformer-based dynamics model for sim-to-real reinforcement learning control of a quadrotor with limited experimental data","year":2025,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Cultural Heritage Administration; Information Technology Research Centre; National Research Institute of Cultural Heritage; Ministry of Science and ICT, South Korea","keywords":"Reinforcement learning; Transformer; Experimental data; Scheme (mathematics); Actuator; Controller (irrigation); Robot; Replicate","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004928659,0.000622798,0.0008507342,0.0003375484,0.0003161522,0.0006869842,0.001109029,0.0009515705,0.004656966],"category_scores_gemma":[0.0008077006,0.0003133448,0.0005303773,0.0002768668,0.0006942489,0.0007186918,0.001081863,0.0008360759,0.0007154847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005190545,"about_ca_system_score_gemma":0.0007530169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006572974,"about_ca_topic_score_gemma":0.004738595,"domain_scores_codex":[0.9997937,0.00004415646,0.00001257516,0.0000549449,0.00006561873,0.00002884407],"domain_scores_gemma":[0.9997171,0.0000839838,0.00005286981,0.00003000023,0.00009540629,0.00002056917],"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":[0.00009023334,0.00002568141,0.0002279787,0.00009764258,0.00002281397,0.00009222238,0.00004713197,0.9720398,0.004299311,0.009989512,0.0005089809,0.01255871],"study_design_scores_gemma":[0.000005968221,0.00001757569,0.00005308026,0.00000269361,0.00000329511,0.000009186499,0.000002993338,0.9985312,0.0002676115,0.0009175615,0.0001862002,0.000002613918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01733924,0.0002062862,0.972844,0.0001997326,0.00008369084,0.00006299886,0.0001367371,0.0004168207,0.008710591],"genre_scores_gemma":[0.9767871,0.0001520342,0.01700346,0.00006555243,0.00001744154,0.0001469126,0.0001028953,0.00004271847,0.00568178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006572974,"threshold_uncertainty_score":0.0155791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02228128544684291,"score_gpt":0.2820420300098923,"score_spread":0.2597607445630493,"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."}}