IMI/Publicaţii/CSJM/Ediţii/CSJM v.12, n.3 (36), 2004/

A New Approach in Agent Path-Finding using State Mark Gradients

Authors: Florin Leon, Mihai Horia Zaharia, Dan Galea
Keywords: Artificial intelligence, path-finding, maze, reinforcement learning, Q-learning, LRTA*, agents.


Since searching is one of the most important problem-solving methods, especially in Artificial Intelligence where it is often difficult to devise straightforward solutions, it has been given continuous attention by researchers. In this paper a new algorithm for agent path-finding is presented. Our approach is based on environment marking during exploration. We tested the performances of Q-learning and Learning Real-Time A* algorithm for three proposed mazes and then a comparison was made between our algorithm, two variants of Q-learning and LRTA* algorithm.

Department of Automatic Control and Computer Engineering,
Technical University "Gh. Asachi",


Adobe PDF document0.26 Mb