{"id":"W4404355808","doi":"10.1016/j.ins.2024.121640","title":"Safe reinforcement learning-based control using deep deterministic policy gradient algorithm and slime mould algorithm with experimental tower crane system validation","year":2024,"lang":"en","type":"article","venue":"Information Sciences","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Tower; Algorithm; Computer science; Reinforcement; Tower crane; Control (management); Artificial intelligence; Engineering; Structural engineering","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":[0.0003384023,0.0001524163,0.0001309782,0.0004185845,0.0003084175,0.0005933157,0.00008353787,0.00004710007,0.00004347208],"category_scores_gemma":[0.0000141919,0.0001263473,0.00002825367,0.0004270994,0.00008843315,0.00134035,0.00001087082,0.0001196179,0.00003071504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002051496,"about_ca_system_score_gemma":0.00007208119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006465086,"about_ca_topic_score_gemma":5.406704e-7,"domain_scores_codex":[0.9988629,0.00002833887,0.0003493685,0.0001265857,0.0004077868,0.0002249955],"domain_scores_gemma":[0.9996723,0.00005436457,0.00007108803,0.00007057696,0.00004851621,0.00008317221],"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":[0.000003103045,0.000002473413,0.00002620701,0.0000545335,0.00001061754,0.000002139579,0.001207896,0.9637457,0.0001041397,0.0002131403,0.000005067519,0.03462497],"study_design_scores_gemma":[0.000365213,0.0001552239,0.00007567867,0.0001112351,0.00001411812,0.00004308013,0.00128975,0.9952595,0.000971015,0.00000224532,0.00154219,0.0001707276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01098297,0.0001409289,0.9859521,0.00003980595,0.0002353461,0.0002446338,0.000001218575,0.0003264186,0.002076562],"genre_scores_gemma":[0.9915211,0.000003435469,0.008268918,0.00006233952,0.00006510726,0.00002219947,0.00001926673,0.000009374434,0.0000282526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9805381,"threshold_uncertainty_score":0.5721357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01513685517039457,"score_gpt":0.2597589877512707,"score_spread":0.2446221325808761,"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."}}