Inicio  /  Applied Sciences  /  Vol: 11 Par: 3 (2021)  /  Artículo
ARTÍCULO
TITULO

Enhanced Reinforcement Learning Method Combining One-Hot Encoding-Based Vectors for CNN-Based Alternative High-Level Decisions

Bonwoo Gu and Yunsick Sung    

Resumen

Gomoku is a two-player board game that originated in ancient China. There are various cases of developing Gomoku using artificial intelligence, such as a genetic algorithm and a tree search algorithm. Alpha-Gomoku, Gomoku AI built with Alpha-Go?s algorithm, defines all possible situations in the Gomoku board using Monte-Carlo tree search (MCTS), and minimizes the probability of learning other correct answers in the duplicated Gomoku board situation. However, in the tree search algorithm, the accuracy drops, because the classification criteria are manually set. In this paper, we propose an improved reinforcement learning-based high-level decision approach using convolutional neural networks (CNN). The proposed algorithm expresses each state as One-Hot Encoding based vectors and determines the state of the Gomoku board by combining the similar state of One-Hot Encoding based vectors. Thus, in a case where a stone that is determined by CNN has already been placed or cannot be placed, we suggest a method for selecting an alternative. We verify the proposed method of Gomoku AI in GuPyEngine, a Python-based 3D simulation platform.

 Artículos similares

       
 
Jiuzhi Fu, Yang Zhang and Yanyue Qin    
In this investigation, the effects of different fabrics with 0.20% carbon fiber textile (CFT), 0.21% glass fiber textile (GFT), and 0.25% basalt fiber textile (BFT) on the properties of TR-UHPC were investigated by axial tensile tests. A bending test of ... ver más
Revista: Applied Sciences

 
Wenhao Ma and Hongzhen Xu    
Cloud computing has experienced rapid growth in recent years and has become a critical computing paradigm. Combining multiple cloud services to satisfy complex user requirements has become a research hotspot in cloud computing. Service composition in mul... ver más
Revista: Applied Sciences

 
Yoshinari Motokawa and Toshiharu Sugawara    
In this paper, we propose an enhanced version of the distributed attentional actor architecture (eDA3-X) for model-free reinforcement learning. This architecture is designed to facilitate the interpretability of learned coordinated behaviors in multi-age... ver más
Revista: Applied Sciences

 
Murad Abu-Farsakh, Mehdi Zadehmohamad and George Z. Voyiadjis    
One of the most effective ways to increase the longevity of pavement structures is through the integration of geosynthetic reinforcement. Geosynthetics are synthetic materials such as geotextiles, geogrids, or geocomposites that are added to the interfac... ver más
Revista: Infrastructures

 
Aristeidis Karras, Christos Karras, Spyros Sioutas, Christos Makris, George Katselis, Ioannis Hatzilygeroudis, John A. Theodorou and Dimitrios Tsolis    
This study explores the design and capabilities of a Geographic Information System (GIS) incorporated with an expert knowledge system, tailored for tracking and monitoring the spread of dangerous diseases across a collection of fish farms. Specifically t... ver más
Revista: Information