Maximum entropy exploration in contextual bandits with neural networks and energy based models

HIGHLIGHTS

• who: Adam Elwood and collaborators from the (UNIVERSITY) have published the article: Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models, in the Journal: Entropy 2023, 25, 188. of /2023/
• what: The authors evaluate the performance of these models in static and dynamic contextual bandit simulation environments. The authors show that both techniques outperform standard baseline algorithms such as NN HMC NN Discrete Upper Confidence Bound and Thompson Sampling where energy based models have the best overall performance. As an alternative to Thompson Sampling and UCB, in this work the authors . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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