Entropy-aware model initialization for effective exploration in deep reinforcement learning

HIGHLIGHTS

• who: Sooyoung Jang and Hyung-Il Kim from the (UNIVERSITY) have published the Article: Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning, in the Journal: Sensors 2022, 22, 5845. of /2022/
• what: This study investigates the effect of initial entropy which significantly influences exploration especially in the early learning stage. The experiments showed that the devised learning strategy significantly reduces learning failures and enhances performance stability and learning speed. The investigations show that the model with low initial entropy significantly increases the probability of learning failures, and that the initial entropy is . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.