Comparison of RBF Network Learning and Reinforcement Learning on the Maze Exploration Problem

Stanislav Slusny, Roman Neruda, Petra Vidnerová

Abstract

An emergence of intelligent behavior within a simple robotic agent is studied in this paper. Two control mechanisms for an agent are considered — a radial basis function neural network trained by evolutionary algorithm, and a traditional reinforcement learning algorithm over a finite agent state space. A comparison of these two approaches is presented on the maze exploration problem.
BibTeX
@inproceedings{slusny2008comparison,
  author = {Stanislav Slusny and Roman Neruda and Petra Vidnerová},
  title = {{Comparison of RBF Network Learning and Reinforcement Learning on the Maze Exploration Problem}},
  booktitle = {ICANN},
  year = {2008},
  doi = {10.1007/978-3-540-87536-9\_74},
}

Loading related content...

Figure