Asynchronous Episodic Deep Deterministic Policy Gradient: Toward Continuous Control in Computationally Complex Environments

强化学习 异步通信 计算机科学 效率低下 任务(项目管理) 理论(学习稳定性) 人工智能 机器学习 工程类 计算机网络 经济 微观经济学 系统工程
作者
Zhizheng Zhang,Jiale Chen,Zhibo Chen,Weiping Li
出处
期刊:IEEE transactions on cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:51 (2): 604-613 被引量:53
标识
DOI:10.1109/tcyb.2019.2939174
摘要

Deep deterministic policy gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially, in computationally complex environments. In this article, we propose asynchronous episodic DDPG (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training stability diminish as the degree of parallelism increases. We consider this problem from the perspectives of both data generation and data utilization. In detail, we redesign experience replay by introducing the idea of episodic control so that the agent can latch on good trajectories rapidly. In addition, we also inject a new type of noise in action space to enrich the exploration behaviors. Experiments demonstrate that our AE-DDPG achieves higher rewards and requires less time consumption than most popular RL algorithms in learning to run task which has a computationally complex environment. Not limited to the control tasks in the computationally complex environments, AE-DDPG also achieves higher rewards and two-fold to four-fold improvement in sample efficiency on average compared with other variants of DDPG in MuJoCo environments. Furthermore, we verify the effectiveness of each proposed technique component through abundant ablation study.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
huan完成签到,获得积分10
刚刚
烛黎完成签到,获得积分10
2秒前
2秒前
唐少北完成签到,获得积分10
2秒前
调皮的沛萍完成签到,获得积分20
5秒前
6秒前
7秒前
7秒前
9秒前
摩丝完成签到,获得积分10
10秒前
10秒前
平常的毛豆应助姜姜采纳,获得30
10秒前
joe发布了新的文献求助10
11秒前
俊逸幻柏发布了新的文献求助10
12秒前
麻吉萌萌完成签到 ,获得积分10
13秒前
LV发布了新的文献求助10
13秒前
13秒前
完美世界应助wzb采纳,获得30
14秒前
15秒前
香蕉觅云应助111采纳,获得10
15秒前
黄龙发布了新的文献求助10
15秒前
能量球发布了新的文献求助10
15秒前
17秒前
朴实乐天完成签到,获得积分10
17秒前
李西瓜发布了新的文献求助10
18秒前
宋北北完成签到,获得积分10
19秒前
深情安青应助俊逸幻柏采纳,获得10
19秒前
DKL完成签到,获得积分10
19秒前
haoryan应助安陌煜采纳,获得10
21秒前
cyan发布了新的文献求助10
22秒前
22秒前
李进发布了新的文献求助10
22秒前
不失眠元菱完成签到,获得积分10
23秒前
23秒前
LV完成签到,获得积分20
23秒前
酷酷的爆米花完成签到,获得积分10
23秒前
25秒前
黄龙完成签到,获得积分10
25秒前
26秒前
上官聪展发布了新的文献求助10
26秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Smart but Scattered: The Revolutionary Executive Skills Approach to Helping Kids Reach Their Potential (第二版) 1000
Very-high-order BVD Schemes Using β-variable THINC Method 830
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3247916
求助须知:如何正确求助?哪些是违规求助? 2891121
关于积分的说明 8266358
捐赠科研通 2559345
什么是DOI,文献DOI怎么找? 1388162
科研通“疑难数据库(出版商)”最低求助积分说明 650698
邀请新用户注册赠送积分活动 627590