Enhanced reinforcement learning method combining one-hot encoding-based vectors for CNN-based alternative high-level decisions
B Gu, Y Sung - Applied Sciences, 2021 - mdpi.com
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 …
cases of developing Gomoku using artificial intelligence, such as a genetic algorithm and a …
Enhanced DQN framework for selecting actions and updating replay memory considering massive non-executable actions
B Gu, Y Sung - Applied Sciences, 2021 - mdpi.com
A Deep-Q-Network (DQN) controls a virtual agent as the level of a player using only
screenshots as inputs. Replay memory selects a limited number of experience replays …
screenshots as inputs. Replay memory selects a limited number of experience replays …
Tafl-ES: Exploring Evolution Strategies for Asymmetrical Board Games
R Gallotta, R Capobianco - … Conference of the Italian Association for …, 2021 - Springer
NeuroEvolution Strategies (NES) are a subclass of Evolution Strategies (ES). While their
application to games and board games have been studied in the past, current state of the art …
application to games and board games have been studied in the past, current state of the art …
[PDF][PDF] Diplomová práca
KI SIETÍ - nil.uniza.sk
ABSTRACT JANOŤÁK, Milan: Access network simulation in OPNET Modeler [diploma
thesis]–The University of Žilina. Faculty of Management Science and Informatics …
thesis]–The University of Žilina. Faculty of Management Science and Informatics …