AI & Medicine

  • Seunghyun Lee [CV]
  • 분류 전체보기 (111)
    • BIOMEDICINE (10)
      • Diabetes (8)
      • Neuroscience (2)
    • AI & RL (64)
      • Meta & Multi-Task RL (11)
      • Foundation Model (4)
      • Representation Learning (8)
      • Causal Inference (16)
      • Privacy-Enhancing Tech. (1)
      • Reinforcement Learning (6)
      • Real-world (Safe) RL (6)
      • Recommender System (6)
      • Model-based RL (1)
      • Human-in-the-Loop RL (2)
      • Combinatorial Opt. (2)
    • MEDICAL & HEALTHCARE AI (28)
    • PERSONAL PROJECTS (9)
      • CV (1)
      • Awards & Honours (2)
      • Book Publications (1)
      • Research Publications (4)
      • Side Projects (1)
    / /

    [북마크] Randomized Ensembled Double Q-Learning: Learning Fast Without a Model (Xinyue Chen, ICLR 2021)

    2021. 5. 24. 16:40

    Author : Xinyue Chen, Che Wang, Zijian Zhou, Keith Ross
    Paper Link : https://arxiv.org/abs/2101.05982

    OpenReview : https://openreview.net/forum?id=AY8zfZm0tDd 

    Code: https://github.com/watchernyu/REDQ

     

    SOTA in Model-free RL

     

    참고자료

    https://www.microsoft.com/en-us/research/blog/three-mysteries-in-deep-learning-ensemble-knowledge-distillation-and-self-distillation/?OCID=msr_blog_ensemble_tw&fbclid=IwAR16837BMbhV0f565yolrGn7vJCGrZxCN6ZTH0TXfUSJin3xkhM5bI4tDJI 

     

    3 deep learning mysteries: Ensemble, knowledge- and self-distillation

    Microsoft and CMU researchers begin to unravel 3 mysteries in deep learning related to ensemble, knowledge distillation & self-distillation. Discover how their work leads to the first theoretical proof with empirical evidence for ensemble in deep learning.

    www.microsoft.com

     

     

    + Recent posts

    Powered by Tistory, Designed by wallel
    Rss Feed and Twitter, Facebook, Youtube, Google+

    티스토리툴바