Combining Deep Deterministic Policy Gradient with Cross-Entropy Method

Tung Yi Lai, Chu Hsuan Hsueh, You Hsuan Lin, Yeong Jia Roger Chu, Bo Yang Hsueh, I. Chen Wu

研究成果: Conference contribution同行評審

摘要

This paper proposes a deep reinforcement learning algorithm for solving robotic tasks, such as grasping objects. We propose in this paper a combination of cross-entropy optimization (CE) with deep deterministic policy gradient (DDPG). More specifically, where in the CE method, we first sample from a Gaussian distribution with zero as its initial mean, we now set the initial mean to DDPG's output instead. The resulting algorithm is referred to as the DDPG-CE method. Next, to negate the effects of bad samples, we improve on DDPG-CE by substituting the CE component with a weighted CE method, resulting in the DDPG-WCE algorithm. Experiments show that DDPG-WCE achieves a higher success rate on grasping previously unseen objects, than other approaches, such as supervised learning, DDPG, CE, and DDPG-CE.

原文English
主出版物標題Proceedings - 2019 International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2019
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781728146669
DOIs
出版狀態Published - 11月 2019
事件24th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2019 - Kaohsiung, Taiwan
持續時間: 21 11月 201923 11月 2019

出版系列

名字Proceedings - 2019 International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2019

Conference

Conference24th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2019
國家/地區Taiwan
城市Kaohsiung
期間21/11/1923/11/19

指紋

深入研究「Combining Deep Deterministic Policy Gradient with Cross-Entropy Method」主題。共同形成了獨特的指紋。

引用此