Institutul de Matematică şi Informatică "Vladimir Andrunachievici"
Universitatea de Stat din MoldovaRO EN
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.
– 0.26 Mb
Keywords: Artificial intelligence, path-finding, maze, reinforcement learning, Q-learning, LRTA*, agents.
Abstract
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",
Iasi
Technical University "Gh. Asachi",
Iasi
Fulltext
– 0.26 Mb
Contents
- Communication Equivalence Classes in Networks
- An algorithm for solving a class of knapsack problems and its generalization
- On stability of an optimal situation in a finite cooperative game with a parametric concept of equilibrium (from lexicographic optimality to Nash equilibrium)
- On stability in game problems of finding Nash set
- The maximum flow in dynamic networks
- The multiobjective transportation fractional programming model
- A New Approach in Agent Path-Finding using State Mark Gradients
- A Case-Based Reasoning for Regulation of an Urban Transportation Network
- Experience of Macroeconomic Models Realization in Transition Economy
- About a family of C2 splines with one free generating function
- The comparative analysis of implementation practices of e-government services
- Electronic Services in Public Administration (e-government); Privacy and Freedom of Information. (review of study made for situation in Moldova)
