{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006115413,0.0003164674,0.0004594311,0.0002496983,0.0003364407,0.0001371783,0.0016775,0.00009381188,0.000001683527],"category_scores_gemma":[0.00005483857,0.0003103489,0.00007611766,0.0005297335,0.00007107371,0.0001811462,0.0003069117,0.0002580224,0.000002758544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001908843,"about_ca_system_score_gemma":0.0003272374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002835706,"about_ca_topic_score_gemma":0.000007694974,"domain_scores_codex":[0.9975643,0.00003298144,0.000672618,0.0006957027,0.0004612809,0.000573183],"domain_scores_gemma":[0.9978971,0.0005584406,0.0003057968,0.0009829628,0.000140831,0.0001148761],"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":[0.0002185667,0.00005677242,0.0002033875,0.0001007054,0.00008683498,6.818117e-7,0.0007074488,0.9620515,0.001684522,0.03168967,0.00003963788,0.003160256],"study_design_scores_gemma":[0.003135468,0.0003690007,0.00002112995,0.0001225982,0.0000401312,5.141865e-7,0.0001899893,0.9933213,0.002343855,0.00003044726,0.0001146259,0.0003109148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005348249,0.000008824315,0.9901378,0.000222114,0.00008735956,0.001792784,0.000006263017,0.0002894259,0.002107182],"genre_scores_gemma":[0.7984232,4.923317e-7,0.200807,0.0004282965,0.00001704444,0.00006997729,0.00008306911,0.0000251674,0.0001456993],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.793075,"threshold_uncertainty_score":0.9999349,"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."}}