Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Hsiang-Yu | en_US |
dc.contributor.author | Wong, Chien-Chou | en_US |
dc.contributor.author | Wong, Sai-Keung | en_US |
dc.date.accessioned | 2020-05-05T00:02:00Z | - |
dc.date.available | 2020-05-05T00:02:00Z | - |
dc.date.issued | 2019-01-01 | en_US |
dc.identifier.isbn | 978-1-7281-4666-9 | en_US |
dc.identifier.issn | 2376-6816 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/154057 | - |
dc.description.abstract | 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. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | reinforcement learning | en_US |
dc.subject | agent-based | en_US |
dc.subject | animation | en_US |
dc.subject | box manipulation | en_US |
dc.title | Effects of Reward Terms in Agent-Based Box-Manipulation Animation Using Deep Reinforcement Learning | en_US |
dc.type | Proceedings Paper | en_US |
dc.identifier.journal | 2019 INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI) | en_US |
dc.citation.spage | 0 | en_US |
dc.citation.epage | 0 | en_US |
dc.contributor.department | 資訊工程學系 | zh_TW |
dc.contributor.department | 電機學院 | zh_TW |
dc.contributor.department | Department of Computer Science | en_US |
dc.contributor.department | College of Electrical and Computer Engineering | en_US |
dc.identifier.wosnumber | WOS:000524126200027 | en_US |
dc.citation.woscount | 0 | en_US |
Appears in Collections: | Conferences Paper |