{"id":"W4405497376","doi":"10.2139/ssrn.5061656","title":"Deep Reinforcement Learning for Methane Slip Reduction in Hybrid-Powered Liquefied Natural Gas Marine Vessels","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Offshore Engineering and Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Methane; Liquefied natural gas; Slip (aerodynamics); Reduction (mathematics); Reinforcement; Natural gas; Reinforcement learning; Environmental science; Petroleum engineering; Waste management; Engineering; Materials science; Computer science; Ecology; Composite material; Biology; Artificial intelligence; Aerospace engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004868296,0.000619167,0.0007688561,0.0002324347,0.0002339774,0.0004568739,0.0006503398,0.0008933311,0.001864002],"category_scores_gemma":[0.001215899,0.0002741636,0.0003092772,0.0001724791,0.0004147663,0.0004096151,0.0006530188,0.0007819348,0.0001541639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005614846,"about_ca_system_score_gemma":0.000706237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01083924,"about_ca_topic_score_gemma":0.006754984,"domain_scores_codex":[0.9998955,0.00002519673,0.000003866166,0.00002456774,0.00001805408,0.00003299928],"domain_scores_gemma":[0.9995978,0.0002345138,0.00003927595,0.00001874071,0.00007517591,0.00003439566],"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":[0.0001065451,0.00004198853,0.0005214245,0.00002334045,0.0000155641,0.00002800477,0.00001114354,0.9790823,0.0008493637,0.0005421535,0.0003222704,0.01845575],"study_design_scores_gemma":[0.000002807328,0.00001239545,0.00005333638,0.000001206158,0.000001390139,0.000001113107,0.000001316502,0.9996417,0.0001104938,0.0001498197,0.00002377164,6.403705e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5418749,0.00100835,0.4484717,0.0005813815,0.0001281277,0.00004865578,0.0001317866,0.0008721139,0.006882983],"genre_scores_gemma":[0.9928215,0.00004010137,0.005789187,0.00002897802,0.00001118326,0.00001351245,0.00003833724,0.00001192483,0.001245278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01083924,"threshold_uncertainty_score":0.02155226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005915983545790707,"score_gpt":0.2237185340921289,"score_spread":0.2178025505463382,"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."}}