QQ客服 官方微博 反馈留言

	Aggregated Multi-Deep Deterministic Policy Gradient for Self-Driving Policy
	Junta Wu; Huiyun Li
	2018
会议日期	2018
会议地点	法国巴黎
英文摘要	Self-driving is a significant application of deep reinforcement learning. We present a deep reinforcement learning algorithm for control policies of self-driving vehicles. This method aggregates multiple sub-policies based on the deep deterministic policy gradient algorithm and centralized experience replays. The aggregated policy converges to the optimal policy by aggregating those sub-optimal sub-policies. It helps reduce the training time largely since each sub-policy is trained with less time. Experimental results on the open racing car simulator platform demonstrates that the proposed algorithm is able to successfully learn control policies, with a good generalization performance. This method outperforms the deep deterministic policy gradient algorithm with 56.7% less training time.
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/13743]
专题	深圳先进技术研究院_集成所
推荐引用方式 GB/T 7714	Junta Wu,Huiyun Li. Aggregated Multi-Deep Deterministic Policy Gradient for Self-Driving Policy[C]. 见:. 法国巴黎. 2018.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。