{"id":"W4402268680","doi":"10.1364/cleo_at.2024.jth2a.143","title":"Deep Transfer Reinforcement Learning in Nanophotonics: A Multi-Objective Inverse Design Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Photonic and Optical Devices","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Nanophotonics; Reinforcement learning; Computer science; Inverse; Transfer of learning; Artificial intelligence; Materials science; Nanotechnology; 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":[0.001009747,0.0007458421,0.000800925,0.0002563657,0.0002286346,0.0006063718,0.0009132056,0.001218216,0.001961767],"category_scores_gemma":[0.001602692,0.0003756199,0.0005353171,0.0002059067,0.0009553244,0.0007259155,0.001134271,0.001432002,0.0002762896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006561227,"about_ca_system_score_gemma":0.0007430437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001580029,"about_ca_topic_score_gemma":0.001259073,"domain_scores_codex":[0.999749,0.00009520484,0.000009261904,0.00003926822,0.0000777728,0.00002938659],"domain_scores_gemma":[0.9995252,0.0002920356,0.00005046454,0.00003305398,0.00006875855,0.00003043705],"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":[0.00003640563,0.00003360324,0.00009718006,0.0000488529,0.0000179041,0.00002943509,0.00002496376,0.9670156,0.002823035,0.01149623,0.0003071789,0.01806965],"study_design_scores_gemma":[0.000003332919,0.00001650438,0.00001067934,0.000002608266,0.000001700769,0.000004177994,0.000001174969,0.9975348,0.0003540041,0.001910798,0.0001580114,0.000002239969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004727692,0.0001288526,0.9934154,0.0001165605,0.00001641936,0.00001749123,0.00000707149,0.0001013053,0.001469222],"genre_scores_gemma":[0.7028694,0.0003013957,0.2899552,0.0002234112,0.00004841287,0.0002677064,0.00004669076,0.0001117999,0.006176051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001961767,"threshold_uncertainty_score":0.006562769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01969828851626191,"score_gpt":0.2232376979547679,"score_spread":0.203539409438506,"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."}}