Jikun Kang

I am a Ph.D. candidate at McGill University. I am fortunate to be advised by Prof. Xue (Steve) Liu.

My research interest lies in the domain of Reinforcement Learning, Meta-RL and Applied RL. Recently, I’m working on improving RL policy generalization and sample-efficiency.

news

Dec 10, 2024	Glad to share that I have been selected as an Outstanding Reviewer for NeurIPS 2024!
Jul 1, 2024	I’m excited to share MindStar, our latest research on large language model reasoning.
May 1, 2024	I’m thrilled to announce our paper “Think Before You Act: Decision Transformers with Internal Memory” is accepted at ICML 2024.
Apr 14, 2024	Our latest paper “Incentive Temperature Control for Green Colocation Data Centers via Reinforcement Learning” has been accepted to the IWQoS 2024.
Dec 23, 2023	Our latest paper LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models has been accepted to AAAI 2024 Human-Centric Representation Learning.

latest posts

Apr 14, 2022	HyperTransformer Model Generation for Supervised and Semi-supervised Few-show Learning
Apr 10, 2022	Online Decision Transformer

selected publications

Preprint

Mindstar: Enhancing math reasoning in pre-trained llms at inference time

Jikun Kang, Xin Zhe Li, Xi Chen, and 8 more authors

arXiv preprint arXiv:2405.16265, 2024

ICML

Think Before You Act: Decision Transformers with Internal Working Memory

Jikun Kang, Romain Laroche, Xindi Yuan, and 3 more authors

arXiv preprint arXiv:2305.16338, 2024

Bib

@article{kang2023think,
  title = {Think Before You Act: Decision Transformers with Internal Working Memory},
  author = {Kang, Jikun and Laroche, Romain and Yuan, Xindi and Trischler, Adam and Liu, Xue and Fu, Jie},
  journal = {arXiv preprint arXiv:2305.16338},
  year = {2024},
}

IWQoS

Incentive Temperature Control for Green Colocation Data Centers via Reinforcement Learning

Rongrong Wang, Duc Van Le, Jikun Kang, and 2 more authors

In IEEE/ACM International Symposium on Quality of Service (IWQoS), 2024

Smart Grid

Peer-to-Peer Energy Trading and Energy Conversion in Interconnected Multi-Energy Microgrids Using Multi-Agent Deep Reinforcement Learning

Tianyi Chen, Shengrong Bu, Xue Liu, and 3 more authors

IEEE Trans. Smart Grid, 2022

Bib

@article{DBLP:journals/tsg/ChenBLKYH22,
  author = {Chen, Tianyi and Bu, Shengrong and Liu, Xue and Kang, Jikun and Yu, F. Richard and Han, Zhu},
  title = {Peer-to-Peer Energy Trading and Energy Conversion in Interconnected
                 Multi-Energy Microgrids Using Multi-Agent Deep Reinforcement Learning},
  journal = {{IEEE} Trans. Smart Grid},
  volume = {13},
  number = {1},
  pages = {715--727},
  year = {2022},
}

CoRL

Learning Multi-Objective Curricula for Robotics Policy Learning

Jikun Kang, Miao Liu, Abhinav Gupta, and 3 more authors

CoRL, 2022

Bib

@article{DBLP:journals/corr/abs-2110-03032,
  author = {Kang, Jikun and Liu, Miao and Gupta, Abhinav and Pal, Chris and Liu, Xue and Fu, Jie},
  title = {Learning Multi-Objective Curricula for Robotics Policy Learning},
  journal = {CoRL},
  volume = {abs/2110.03032},
  year = {2022},
}