Matthew Schlegel

Matthew Schlegel

Lover of Espresso; PhD student at Amii, RLAI and UofA; Works on how machines perceive their world.

  • Edmonton, Alberta
  • LinkedIn
  • Twitter
  • Github
  • Tags
  • Collections
Home About CV Publications Code BrainDump

Temporal Difference Learning

Nov 9, 2022
tags
Reinforcement Learning

This is a method for learning Value Functions and was first described by (Sutton 1988).

References

Sutton, Richard S. 1988. “Learning to Predict by the Methods of Temporal Differences.” Machine Learning.

Links to this note:

  • sutton1988learning: Learning to predict by the methods of temporal differences

Copyright © 2020 Matthew Schlegel. All Rights Reserved. Powered by Hugo and Minimal Academic.