Current Time 0:00
/
Duration Time 0:00
Progress: NaN%
Playback Rate
1.00x

Parallel reinforcement learning: a framework and case study

Research Square

Research Square

  • First Author :
    Teng Liu
  • Co-authors :
    Bin Tian ; Yunfeng Ai ; Li Li ; Dongpu Cao ; Fei-Yue Wang
  • Journal Name :
    IEEE Xplore
  • Read Full text :
  • DOI :
    10.1109/JAS.2018.7511069

Share This Video

Abstract

In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is built to improve complex learning system by self-guidance. Based on the Markov chain (MC) theory, we combine the transfer learning, predictive learning, deep learning and reinforcement learning to tackle the data and action processes and to express the knowledge. Parallel reinforcement learning framework is formulated and several case studies for real-world problems are finally introduced.

Ask Questions 0

Please Login or Register to add your question

Recommended Videos

No recommendation found