ON THE DEVELOPMENT OF AUTONOMOUS AGENTS USING DEEP REINFORCEMENT LEARNING

被引：0

作者：

Barbu, Clara ^{[1
]}

Mocanu, Stefan Alexandru ^{[2
]}

机构：

[1] Univ Politehn Bucuresti, Fac Automat Control & Comp Sci, Bucharest, Romania

[2] Univ Politehn Bucharesti, Fac Automat Control & Comp Sci, Bucharest, Romania

来源：

UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE | 2021年 / 83卷 / 03期

关键词：

reinforcement learning; Q-learning; autonomous agent; autonomous vehicle; Deep Learning; Experience Replay; Unity3D;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper presents a study on the general concept of autonomous agents, with an accent on the development of such agents using deep reinforcement learning. This is combined with the domain of autonomous vehicles, as illustrated by a practical application: having a vehicle agent learn how to navigate and park by itself on a designated spot, in a virtual parking lot environment created in Unity. The reinforcement learning method Deep Q-Learning is implemented, with the addition of a few improvements such as Double Deep Q-Learning and Experience Replay.

引用

页码：97 / 116

页数：20

共 22 条

[1] [Anonymous], 1993, P TECHN REP DTIC DOC, DOI 10.5555/168871
[2] [Anonymous], 2018, ARXIV180310122
[3] [Anonymous], 2013, Playing atari with deep reinforcement learning
[4] Arzt Samuel, 2019, LEARNS PARK DEEP REI
[5] INTELLIGENCE WITHOUT REPRESENTATION
BROOKS, RA
[J]. ARTIFICIAL INTELLIGENCE, 1991, 47 (1-3) : 139 - 159
[6] DeepMind Technologies, ALPHAGO
[7] della Cava M., 2019, USA TODAY
[8] Juliani A., 2020, ARXIV PREPRINT ARXIV
[9] Kendall A., 2018, 180700412 ARXIV
[10] Lillicrap Timothy P, 2016, 4 INT C LEARN REPRES

← 1 2 3 →