{"id":197089,"date":"2025-06-18T13:53:32","date_gmt":"2025-06-18T04:53:32","guid":{"rendered":"http:\/\/ee.presscat.kr\/?post_type=research-achieve&p=197089"},"modified":"2026-04-13T03:47:43","modified_gmt":"2026-04-12T18:47:43","slug":"professor-youngchul-sungs-labs-phd-student-jeonghye-kim-contributes-to-industrial-site-optimization-with-ai","status":"publish","type":"research-achieve","link":"http:\/\/ee.presscat.kr\/en\/research-achieve\/professor-youngchul-sungs-labs-phd-student-jeonghye-kim-contributes-to-industrial-site-optimization-with-ai\/","title":{"rendered":"Professor Youngchul Sung\u2019s Lab\u2019s PhD Student Jeonghye Kim Contributes to Industrial Site Optimization with AI"},"content":{"rendered":"
\"\"
<Kim Jeong-hye PhD Student><\/span><\/figcaption><\/figure>\n

Alongside large language models, autonomous driving and humanoid robots, AI-driven optimization of industrial manufacturing has emerged as a major application of AI. In 2024, Kim Jeong-hye, a PhD student of Professor Youngchul Sung, interned on LG AI Research\u2019s reinforcement-learning team, where she tackled a range of process-optimization challenges across LG Group\u2019s production facilities.<\/span><\/p>\n

That team applied optimization majorly based on reinforcement learning to LG Chem\u2019s Daesan plant\u2019s naphtha-cracking facility (NCC), improving production efficiency by 3%, far beyond of 0.1% of initial expectation, and yielding an extra KRW 10 billion in annual profit for that plant alone. Because training reinforcement learning agents via on-line interaction in a production environment is impractical, such optimization typically relies on offline reinforcement learning, which optimizes policies with pre-collected data.<\/span><\/p>\n

Jeonghye contributed to the development of PARS, a novel offline reinforcement learning algorithm that significantly outperforms existing methods. By enhancing the neural network\u2019s feature resolution with reward scaling with layer normalization, this new approach better differentiates between in-sample and out-of-distribution data, eliminating Q-value divergence, the core issue of off-line reinforcement learning. This advancement promises to accelerate future production-process optimizations as well as many RL applications with difficulty in on-line environment interaction.\u00a0<\/span><\/p>\n

This research result will be presented as a Spotlight paper at the International Conference on Machine Learning (ICML) 2025.<\/span><\/p>\n

Related Yonhap News article: \u00a0https:\/\/www.yna.co.kr\/view\/AKR20250613153400003<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

260<\/p>\n","protected":false},"featured_media":197088,"template":"","research_category":[347],"class_list":["post-197089","research-achieve","type-research-achieve","status-publish","has-post-thumbnail","hentry","research_category-ai-machine-learning-en"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve\/197089","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/research-achieve"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media\/197088"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=197089"}],"wp:term":[{"taxonomy":"research_category","embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research_category?post=197089"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}