Skip to Content
Reinforcement Learning with TensorFlow
book

Reinforcement Learning with TensorFlow

by Sayon Dutta
April 2018
Intermediate to advanced content levelIntermediate to advanced
334 pages
10h 18m
English
Packt Publishing
Content preview from Reinforcement Learning with TensorFlow

Mixed objective using self-critical policy learning

A DCN creates a probability distribution on the start position of the answer and a separate probability distribution on the end position of the answer. At each decoding time step, the model aggregates the cross-entropy loss for each position. The question answering task comprises of two evaluation metrics. They are as follows:

  • Exact match: A binary value indicating that the answer span output by the model has an exact string match with the ground truth answer span
  • F1-score: A value quantifying the degree of overlapping of words between the predicted answer span by the model and the ground truth answer span

As per the original DCN framework, the objective function and evaluation metric ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Deep Learning with TensorFlow - Second Edition

Deep Learning with TensorFlow - Second Edition

Giancarlo Zaccone, Vihan Jain, Md. Rezaul Karim, Motaz Saad
Deep Learning with TensorFlow 2 and Keras - Second Edition

Deep Learning with TensorFlow 2 and Keras - Second Edition

Antonio Gulli, Dr. Amita Kapoor, Sujit Pal

Publisher Resources

ISBN: 9781788835725Supplemental Content