Jikun Kang

Room 305

McConnel Building

McGill University

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 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.
May 28, 2023	Thrilled to see that my recent research with MSR has garnered attention from the community.twitter
Jan 18, 2023	Happy to share our paper “Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks” was accepted at IEEE International Conference on Communications (ICC) 2023!
Sep 10, 2022	I’m thrilled to announce that our latest paper “Learning Multi-Objective Curricula for Robotic Policy Learning” has been accepted to CoRL 2022.
Aug 2, 2022	Our latest paper about how to improve policy generalization in real-world application (5G networking) has been accepted to GlobeCOM2022!

selected publications

CoRL

Learning Multi-Objective Curricula for Robotics Policy Learning

Kang, Jikun, Liu, Miao, Gupta, Abhinav, Pal, Chris, Liu, Xue, and Fu, Jie

CoRL 2022

Bib

@article{DBLP:journals/corr/abs-2110-03032,
  abbr = {CoRL},
  bibtex_show = {true},
  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},
  selected = {true}
}

Globecom

A Generalized Load Balancing Policy With Multi-Teacher Reinforcement Learning

Kang, Jikun, Wang, Ju, Hu, Chengming, Liu, Xue, and Dudek, Gregory

In GLOBECOM 2022

Bib

@inproceedings{DBLP:conf/globecom/2022,
  abbr = {Globecom},
  bibtex_show = {true},
  author = {Kang, Jikun and Wang, Ju and Hu, Chengming and Liu, Xue and Dudek, Gregory},
  title = {A Generalized Load Balancing Policy With Multi-Teacher Reinforcement Learning},
  booktitle = {{GLOBECOM}},
  publisher = {{IEEE}},
  year = {2022},
  selected = {true}
}

ICC

Hierarchical Policy Learning for Hybrid Communication Load Balancing

Kang, Jikun, Chen, Xi, Wu, Di, Xu, Yi Tian, Liu, Xue, Dudek, Gregory, Lee, Taeseop, and Park, Intaik

In ICC 2021

Bib

@inproceedings{DBLP:conf/icc/KangCWXLDLP21,
  abbr = {ICC},
  bibtex_show = {true},
  author = {Kang, Jikun and Chen, Xi and Wu, Di and Xu, Yi Tian and Liu, Xue and Dudek, Gregory and Lee, Taeseop and Park, Intaik},
  title = {Hierarchical Policy Learning for Hybrid Communication Load Balancing},
  booktitle = {{ICC}},
  pages = {1--6},
  publisher = {{IEEE}},
  year = {2021},
  selected = {true}
}

Globecom

Load Balancing for Communication Networks via Data-Efficient Deep Reinforcement Learning

Wu, Di, Kang, Jikun, Xu, Yi Tian, Li, Hang, Li, Jimmy, Chen, Xi, Rivkin, Dmitriy, Jenkin, Michael, Lee, Taeseop, Park, Intaik, Liu, Xue, and Dudek, Gregory

In GLOBECOM 2021

Bib

@inproceedings{DBLP:conf/globecom/WuKXLLCRJLPLD21,
  abbr = {Globecom},
  bibtex_show = {true},
  author = {Wu, Di and Kang, Jikun and Xu, Yi Tian and Li, Hang and Li, Jimmy and Chen, Xi and Rivkin, Dmitriy and Jenkin, Michael and Lee, Taeseop and Park, Intaik and Liu, Xue and Dudek, Gregory},
  title = {Load Balancing for Communication Networks via Data-Efficient Deep
                 Reinforcement Learning},
  booktitle = {{GLOBECOM}},
  pages = {1--7},
  publisher = {{IEEE}},
  year = {2021},
  selected = {true}
}

NeurIPS

Multi-Agent Option Critic Architecture

Goupta, Abhinav, Chakravorty, Jhelum, Kang, Jikun, Liu, Xue, Pal, Christopher, and Precup, Doina

In Neural Information Processing Systems (NeurIPS) workshops in Deep Reinforcement Learning 2020

ICC

Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks

Kang, Jikun, Wu, Di, Wang, Ju, Liu, Xue, and Dudek, Gregory

In ICC 2023

Bib

@inproceedings{DBLP:conf/icc/Kang23,
  abbr = {ICC},
  bibtex_show = {true},
  author = {Kang, Jikun and Wu, Di and Wang, Ju and Liu, Xue and Dudek, Gregory},
  title = {Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks},
  booktitle = {{ICC}},
  publisher = {{IEEE}},
  pages = {1--6},
  year = {2023},
  selected = {true}
}

preprint

Think Before You Act: Decision Transformers with Internal Working Memory

Kang, Jikun, Laroche, Romain, Yuan, Xindi, Trischler, Adam, Liu, Xue, and Fu, Jie

arXiv preprint arXiv:2305.16338 2023

Bib

@article{kang2023think,
  abbr = {preprint},
  bibtex_show = {true},
  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 = {2023},
  selected = {true}
}