Byung-Jun Lee (이병준)

Email: bjlee@ai.kaist.ac.kr

Research Interest: offline, model-based, off-policy reinforcement learning. probabilistic models and dialog management.

2015. 03. - 2021. 02. (expected) : Ph. D. Candidate, School of Computing, KAIST
(Advisor: Kee-Eung Kim)


Publications

  • Byung-Jun Lee, Jongmin Lee and Kee-Eung Kim, "Representation balancing offline model-based reinforcement learning", under review.

  • Deunsol Yoon*, Sunghoon Hong*, Byung-Jun Lee and Kee-Eung Kim, "Winning the L2RPN challenge: power grid management via semi-Markov afterstate actor-critic", under review (*: equally contributed).

  • Jongmin Lee, Byung-Jun Lee and Kee-Eung Kim, "Reinforcement learning for control with multiple frequencies", in Thirty-Fourth Annual Conference on Neural Information Processing Systems (NeurlPS), 2020

  • Byung-Jun Lee*, Jongmin Lee*, Peter Vrancx, Dongho Kim and Kee-Eung Kim, "Batch reinforcement learning with hyperparameter gradients", in International Conference on Machine Learning (ICML), 2020 (*: equally contributed)

  • Byung-Jun Lee, Seunghoon Hong and Kee-Eung Kim, "Residual neural processes", in AAAI conference on Artificial Intelligence (AAAI), 2020

  • Youngsoo Jang, Jiyeon Ham, Byung-Jun Lee and Kee-Eung Kim, "Cross-language neural dialog state tracker for large ontologies using hierarchical attention", IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2018

  • Byung-Jun Lee, Jongmin Lee and Kee-Eung Kim, "Hierarchically-partitioned Gaussian process approximation", in International Conference on Artificial Intelligence and Statistics (AISTATS), 2017

  • Youngsoo Jang, Jiyeon Ham, Byung-Jun Lee, Youngjae Chang and Kee-Eung Kim, "Neural dialog state tracker for large ontologies by attention mechanism", in IEEE Spoken Language Technology Workship (SLT), 2016

  • Byung-Jun Lee and Kee-Eung Kim, "Dialog history construction with long-short term memory for robust generative dialog state tracking", in Dialogue & Discourse (D&D), 2016

  • Byung-Jun Lee and Kee-Eung Kim, "Optimizing Bayesian filtering model for statistical dialog state tracking", Master thesis, 2015

  • Byung-Jun Lee, Woosang Lim, Daejoong Kim and Kee-Eung Kim, "Optimizing generative dialog state tracker via cascading gradient descent", in Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2014

Experiences

  • 2018. 01. - 2018. 07. Machine learning research intern, PROWLER.io (Current Secondmind)

Awards and Honors

  • Learning to Run a Power Network Challenge (L2RPN) 2020 WCCI (1st place), 2020

  • Naver Ph.D. Fellowship, Naver, 2017