Skip to content. | Skip to navigation

Personal tools
Log in
Sections
You are here: Home People Jaedeug Choi

Jaedeug Choi (최재득)

by Jaedeug Choi last modified Feb 12, 2014 10:34 PM

 

 

I did my Ph.D. under the supervision of Prof. Kee-Eung Kim at the Department of Computer Science, Korea Advanced Institute of Science and Technology (KAIST) in Aug. 2013. I am interested in planning, learning, and decision making under uncertainty. My recent research focuses on inverse reinforcement learning and its applications.

 

Research Interests

Machine Learning Theory:

Reinforcement learning, partially observable Markov decision process (POMDP), inverse reinforcement learning (IRL), Bayesian nonparametrics

Machine Learning Applications:

Human behavior understanding, collaborative filtering and recommendation, spoken dialog management

 

Education

Ph.D. in Department of Computer Science, KAIST, Aug. 2013.
Thesis: Models and Algorithms for Inverse Reinforcement Learning
Supervisor: Prof. Kee-Eung Kim

M.S. in Department of Computer Science, KAIST, Aug. 2009.
Thesis: Inverse Reinforcement Learning in Partially Observable Environments
Supervisor: Prof. Kee-Eung Kim

B.S. in Department of Computer Science and Engineering, POSTECH, Feb. 2007.

 

Publications

Daejoong Kim, Jaedeug Choi, Kee-Eung Kim, Jungsu Lee, and Jinho Sohn
Engineering Statistical Dialog State Trackers: A Case Study on DSTC
Proceedings of the SIGDIAL 2013 Conference.

Jaedeug Choi and Kee-Eung Kim 
Bayesian Nonparametric Feature Construction for Inverse Reinforcement Learning (code)
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). 2013.
(acceptance ratio=413/1473=28%)

Jaedeug Choi and Kee-Eung Kim
Nonparametric Bayesian Inverse Reinforcement Learning for Multiple Reward Functions (code, video)
Proceedings of Neural Information Processing Systems (NIPS). 2012.
(acceptance ratio=370/1467=25%)

Dongho Kim, Jaesong Lee, Jaedeug Choi, and Kee-Eung Kim
A POMDP Frame-work for Dynamic Task Allocation and Reconnaissance of Multiple Unmanned Aerial Vehicels
Journal of Korean Institute of Information Scientists and Engineers (KIISE):Software and Applications, 39(6). 2012.

Jaedeug Choi and Kee-Eung Kim
MAP Inference for Bayesian Inverse Reinforcement Learning
Proceedings of Neural Information Processing Systems (NIPS). 2011. 
(acceptance ratio=305/1400=22%)

Jaedeug Choi and Kee-Eung Kim
Inverse Reinforcement Learning in Partially Observable Environments (code)
Journal of Machine Learning Research (JMLR), 12. 2011.

Jaedeug Choi and Kee-Eung Kim
Inverse Reinforcement Learning in Partially Observable Environments
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). 2009.
(acceptance ratio=331/1290=26%)

Jaedeug Choi, WoonHyun Nam, and JoonHee Han
A Master-Slave Camera System using a Homography of an Imaginary Plane
Workshop on Image Processing and Image Understandings (IPIU), 2008.

 

Academic Activities

Conference Reviews

NIPS 2013, ACML 2013

Affiliation

Institute of Electrical and Electronic Engineers (IEEE) 
Korean Institute of Information Scientists and Engineers (KIISE)

Miscellaneous

IRL tutorial (slides) at Pattern Recognition and Machine Learning Summer School 2013 (hosted by KIISE)
Participated in Dialog State Tracking Challenge (DSTC) 2013

 

Awards & Scholarships

2012 NIPS travel award
2011 NIPS travel award
2010 Outstanding M.S. thesis award in Department of Computer Science, KAIST
2009 IJCAI travel award
2007 Best oral presentation at Undergraduate Research Program, POSTECH

 

Contact

Department of Computer Science
Korea Advanced Institute of Science and Technology (KAIST)
335 Gwahangno, Yuseong-gu, Daejeon, 305-701, Republic of Korea

Office: E3-1 #2418
Tel: +83-42-350-7736
E-mail: jdchoi [at] ai [dot] kaist [dot] ac [dot] kr

 

Flag Counter