標題: Effects of Reward Terms in Agent-Based Box-Manipulation Animation Using Deep Reinforcement Learning
作者: Yang, Hsiang-Yu
Wong, Chien-Chou
Wong, Sai-Keung
資訊工程學系
電機學院
Department of Computer Science
College of Electrical and Computer Engineering
關鍵字: reinforcement learning;agent-based;animation;box manipulation
公開日期: 1-Jan-2019
摘要: Agent-based box manipulation has wide applications in computer animation and robotics. Deep reinforcement learning can be applied to generate animations of agent-based box manipulation. This paper focuses on push-manipulation in an agent-based animation. A policy is learned in a learning session in which an agent receives a reward that is a combination of different types of reward terms. Based on the received reward, the policy is improved gradually. In this paper, we investigate the effects of each reward term in-depth in a framework that is integrated with deep reinforcement learning. We also propose a simple way to produce different animation types. We performed several examples and analyzed our findings in details.
URI: http://hdl.handle.net/11536/154057
ISBN: 978-1-7281-4666-9
ISSN: 2376-6816
期刊: 2019 INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI)
起始頁: 0
結束頁: 0
Appears in Collections:Conferences Paper