Neural Fitted Q Iteration – First Experiences with a Data Efficient Neural Reinforcement Learning Method

This publication has 4 references indexed in Scilit:

• A direct adaptive method for faster backpropagation learning: the RPROP algorithm
  Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
• 10.1162/jmlr.2003.4.6.1107
  Applied Physics Letters, 2000
• Concepts and Facilities of a Neural Reinforcement Learning Control Architecture for Technical Process Control
  Neural Computing & Applications, 1999
• Stable Function Approximation in Dynamic Programming
  Published by Elsevier ,1995