Neural fitted q iteration – first experiences with a data efficient neural reinforcement learning method

@inproceedings{Riedmiller2005NeuralFQ,
  title={Neural fitted q iteration – first experiences with a data efficient neural reinforcement learning method},
  author={Martin A. Riedmiller},
  booktitle={ECML},
  year={2005}
}
This paper introduces NFQ, an algorithm for efficient and effective training of a Q-value function represented by a multi-layer perceptron. Based on the principle of storing and reusing transition experiences, a model-free, neural network based Reinforcement Learning algorithm is proposed. The method is evaluated on three benchmark problems. It is shown empirically, that reasonably few interactions with the plant are needed to generate control policies of high quality. 
Highly Influential
This paper has highly influenced 75 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 776 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 362 extracted citations

Learning state representation for deep actor-critic control

2016 IEEE 55th Conference on Decision and Control (CDC) • 2016
View 10 Excerpts
Method Support
Highly Influenced

Learning robotic soccer controllers with the Q-Batch update-rule

2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC) • 2014
View 5 Excerpts
Highly Influenced

Reinforcement learning for robot soccer

View 13 Excerpts
Method Support
Highly Influenced

An intelligent scheduling algorithm for resource management of cloud platform

Multimedia Tools and Applications • 2018
View 4 Excerpts
Highly Influenced

Approximate Value Iteration Based on Numerical Quadrature

IEEE Robotics and Automation Letters • 2018
View 8 Excerpts
Highly Influenced

Deep Reinforcement Learning: An Overview

View 6 Excerpts
Method Support
Highly Influenced

776 Citations

050100'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 776 citations based on the available data.

See our FAQ for additional information.