Author:
Narita Riku, ,Kurashige Kentarou
Abstract
Reinforcement learning can lead to autonomous behavior depending on the environment. However, in complex and high-dimensional environments, such as real environments, a large number of trials are required for learning. In this paper, we propose a solution for the learning problem using local learning to select an action based on the surrounding environmental information. Simulation experiments were conducted using maze problems, pitfall problems, and environments with random agents. The actions that did not contribute to task accomplishment were compared between the proposed method and ordinary reinforcement learning method.
Publisher
Fuji Technology Press Ltd.
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Human-Computer Interaction
Reference25 articles.
1. T. Hashimoto, X. Tao, T. Suzuki, T. Kurose, Y. Nishikawa, and Y. Kagawa, “Decision Making of Communication Robots Through Robot Ethics,” J. Adv. Comput. Intell. Intell. Inform., Vol.25, No.4, pp. 467-477, 2021.
2. Y. Yamazaki, M. Ishii, T. Ito, and T. Hashimoto, “Frailty Care Robot for Elderly and its Application for Physical and Psychological Support,” J. Adv. Comput. Intell. Intell. Inform., Vol.25, No.6, pp. 944-952, 2021.
3. J. H. Connell and S. Mahadevan, “Robot Learning,” Kluwer Academic Publishers, 1993.
4. N. T. Thinh, T. P. Tho, and N. D. X. Hai, “Adaptive Fuzzy Control for Autonomous Robot under Complex Environment,” Int. J. Mech. Eng. Robot. Res., Vol.10, No.5, pp. 216-223, 2021.
5. R. S. Sutton and A. G. Barto, “Reinforcement learning,” J. Cogn. Neurosci., Vol.11, No.1, pp. 126-134, 1999.