Seungchan Kim

email: seungch2@andrew.cmu.edu

I am a first-year PhD student in the Robotics Institute at Carnegie Mellon University, advised by Professor Sebastian Scherer. My research interests are at the intersection of robotics and reinforcement learning.

Previously, I received B.S. in Applied Mathematics & Computer Science and M.S. in Computer Science from Brown University. During my time at Brown, I worked with Professor George Konidaris and Michael Littman, focusing on research in deep reinforcement learning.

CV  /  GitHub  /  Google Scholar  /  Twitter

profile photo
Publications
Combating the Compounding-Error Problem with a Multi-step Model
Kavosh Asadi, Dipendra Misra, Seungchan Kim, Michael Littman
arXiv preprint. CoRR abs/1905.13320 [cs.LG]
Adaptive Temperature Tuning for Mellowmax in Deep Reinforcement Learning
Seungchan Kim, George Konidaris
NeurIPS 2019 Deep Reinforcement Learning Workshop
DeepMellow: Removing the Need for a Target Network in Deep Q-Learning
Seungchan Kim, Kavosh Asadi, Michael Littman, George Konidaris
Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019)
The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2019)
project page / code
Removing the Target Network from Deep Q-Networks with the Mellowmax Operator
Seungchan Kim, Kavosh Asadi, Michael Littman, George Konidaris
Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019)
Teaching
CSCI1430 Computer Vision, Brown University
Teaching Assistant, Spring 2019

CSCI0040 Intro to Scientific Computing and Problem Solving, Brown University
Teaching Assistant, Spring 2015
Service
Conference Reviewer: ICML 2020, AAAI 2021, ICLR 2021
Workshop Reviewer:
- NeurIPS 2019 Workshop on ML for Health, Workshop on ML and Physical Sciences
- NeurIPS 2020 Workshop on the Challenges of Real-World Reinforcement Learning

Website Template from Jon Barron.