Knowledge Commons of Institute of Automation,CAS
Visual navigation with Actor-Critic deep reinforcement learning | |
Kun Shao1,2; Dongbin Zhao1,2; Yuanheng Zhu1,2; Qichao Zhang1,2 | |
2018-03 | |
会议名称 | IEEE International Joint Conference on Neural Networks |
会议日期 | 2018-01 |
会议地点 | Rio, Brazil |
摘要 | Visual navigation in complex environments is crucial for intelligent agents. In this paper, we propose an efficient deep reinforcement learning (DRL) method to tackle visual navigation tasks. We present the synchronous advantage actor-critic (A2C) with generalized advantage estimator (GAE) algorithm. The A2C enables agents to learn from multiple processes, which significantly reduces the training time. The GAE used to estimate the advantage function improves the policy gradient estimates. We focus on visual navigation tasks in ViZDoom, and train agents in two health gathering scenarios. The experimental results show this method successfully teaches our agents to navigate in these scenarios. The A2C with GAE agent reaches the highest score |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23365 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
通讯作者 | Yuanheng Zhu |
作者单位 | 1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Kun Shao,Dongbin Zhao,Yuanheng Zhu,et al. Visual navigation with Actor-Critic deep reinforcement learning[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Visual Navigation wi(1827KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论