Deep learning with intelligent opponent in fencing

Deep learning with intelligent opponent in fencing

VR technologies have enabled the development of virtual sports games, which greatly enhance the accessibility of physical sport by making it available virtually. Considering there is currently no such game for fencing, this project aims to design and develop a VR fencing game. For now, we have desig...

Full description

Saved in:
Bibliographic Details
Main Author: Loh, Qiao Yan
Other Authors: Seah Hock Soon
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Online Access:https://hdl.handle.net/10356/156771
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:VR technologies have enabled the development of virtual sports games, which greatly enhance the accessibility of physical sport by making it available virtually. Considering there is currently no such game for fencing, this project aims to design and develop a VR fencing game. For now, we have designed and implemented a fencer avatar to act in the virtual environment and conducted several reinforcement learning experiments to train an intelligent fencing agent as the game opponent. Training of the agent is conducted in a self-play setting. The training result showed that there is a need to further improve the action space of the agent.

Similar Items