{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001441446,0.001043434,0.0005957125,0.0005722973,0.0004834874,0.0005307849,0.0007703365,0.0008613803,0.002138194],"category_scores_gemma":[0.002776993,0.0003091163,0.0005446619,0.0002425511,0.0007146782,0.0005137373,0.0007259681,0.001343153,0.0002115216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008409498,"about_ca_system_score_gemma":0.00136539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02304595,"about_ca_topic_score_gemma":0.01645408,"domain_scores_codex":[0.9996254,0.0001000526,0.00002357729,0.00006805017,0.0001118352,0.00007110585],"domain_scores_gemma":[0.9982834,0.0008199289,0.0001621043,0.0001935217,0.0004592094,0.00008191849],"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":[0.0001365331,0.0001142216,0.00113309,0.0001219166,0.00003067882,0.000056557,0.0000727966,0.9739593,0.004313154,0.001381034,0.0004593774,0.01822124],"study_design_scores_gemma":[0.00001292008,0.00006039774,0.0002445567,0.00000560554,0.00000366712,0.000003771472,0.000007573135,0.9975309,0.001780774,0.0002057129,0.0001392111,0.000004848868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4606497,0.000709739,0.5184067,0.0004430618,0.0001987784,0.0002852702,0.000208653,0.003963768,0.01513427],"genre_scores_gemma":[0.9786547,0.00003168085,0.02003092,0.00002277692,0.000002538947,0.00008560498,0.00007160249,0.00003887387,0.001061319],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02304595,"threshold_uncertainty_score":0.04582363,"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."}}