Yachen Kang

Yachen Kang

Joint Ph.D. Student @ Westlake University & Zhejiang University

Yachen Kang 亢雅宸

Hi! I am Yachen Kang (亢雅宸 in Chinese). I am a Ph.D. student of Zhejiang University, advised by Dr. Donglin Wang. Also, I am a member of Machine Intelligence Laboratory (MiLAB) in Westlake University, where I do my research work on machine learning and robot learning. Prior to my Ph.D. career, I obtained my bachelor’s degree of Engineering from School of Electronic Science and Engineering, Nanjing University in 2018, majoring in Biomedical Engineering.

I am seeking exciting industry opportunities for both research and applications after Ph.D. graduation (June 2024). Please feel free to drop me an email if you are interested!

Publications

Beyond Reward: Offline Preference-guided Policy Optimization

  • Yachen Kang, Diyuan Shi, Jinxin Liu, Li He, Donglin Wang
  • In Proceedings of the Fortieth International Conference on Machine Learning (ICML), 2023
  • [paper] [code] [project]

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

  • Jinxin Liu, Hao Shen, Donglin Wang, Yachen Kang, Qiangxing Tian
  • In Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021

Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition

  • Siteng Huang, Min Zhang, Yachen Kang, Donglin Wang
  • In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), 2021
  • [paper] [code] [project]

Deep Transfer Collaborative Filtering with Geometric Structure Preservation for Cross-Domain Recommendation

  • Yachen Kang, Sibo Gai, Feng Zhao, Donglin Wang, Ao Tang
  • In Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), 2020

Independent Skill Transfer for Deep Reinforcement Learning

  • Qiangxing Tian, Guanchu Wang, Jinxin Liu, Donglin Wang, Yachen Kang
  • In Proceedings of the 2020 International Joint Conferences on Artificial Intelligence (IJCAI), 2020

Cross-domain deep collaborative filtering for recommendation

  • Yachen Kang, Sibo Gai, Feng Zhao, Donglin Wang, Yi Luo
  • In Proceedings of the 2019 International Conference on Data Mining Workshops (ICDMW), 2019

Deep transfer collaborative filtering for recommender systems

  • Sibo Gai, Feng Zhao, Yachen Kang, Zhengyu Chen, Donglin Wang, Ao Tang
  • In Proceedings of the Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2020

Preprint

STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization

  • Yachen Kang, Li He, Jinxin Liu, Zifeng Zhuang, Donglin Wang
  • arXiv, 2022
  • [paper]

Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain

  • Yachen Kang, Jinxin Liu, Xin Cao, Donglin Wang
  • arXiv, 2021
  • [paper] [code]

CEIL: Generalized Contextual Imitation Learning

  • Jinxin Liu, Li He, Yachen Kang, Zifeng Zhuang, Donglin Wang, Huazhe Xu
  • arXiv, 2023
  • [paper]

Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization

  • Jinxin Liu, Hongyin Zhang, Zifeng Zhuang, Yachen Kang, Donglin Wang, Bin Wang
  • arXiv, 2023
  • [paper]

Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning

  • Jinxin Liu, Ziqi Zhang, Zhenyu Wei, Zifeng Zhuang, Yachen Kang, Sibo Gai, Donglin Wang
  • arXiv, 2023
  • [paper]