2021
DOI: 10.1109/comst.2021.3073036
|View full text |Cite
|
Sign up to set email alerts
|

Deep Reinforcement Learning for Internet of Things: A Comprehensive Survey

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
43
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 162 publications
(58 citation statements)
references
References 150 publications
0
43
0
Order By: Relevance
“…The recent advances in DRL algorithms can potentially address the above problems of IoT systems. Chen et al [28] did a comprehensive survey and provided a state-of-the-art literature review on a wide variety of IoT applications enabled by DRL algorithms. Therefore, some researchers combine neural networks and reinforcement learning in dealing with task offloading problems to explore unknown complex dynamic IoT environment information to make decisions.…”
Section: Offloading Methods With Different Problem Solving Strategiesmentioning
confidence: 99%
“…The recent advances in DRL algorithms can potentially address the above problems of IoT systems. Chen et al [28] did a comprehensive survey and provided a state-of-the-art literature review on a wide variety of IoT applications enabled by DRL algorithms. Therefore, some researchers combine neural networks and reinforcement learning in dealing with task offloading problems to explore unknown complex dynamic IoT environment information to make decisions.…”
Section: Offloading Methods With Different Problem Solving Strategiesmentioning
confidence: 99%
“…An AI machine should come through trial and error to reach a nearly optimal solution for a game-like scenario. The object of an RL model is how to perform the task to maximize the reward and minimize the penalty, beginning with totally random trials and ending with sophisticated tactics and superhuman skills [10]. By exploiting the power of the searching scheme with many trials, RL is one of the most effective ways to imply machine creativity.…”
Section: A Categorization Of Aimentioning
confidence: 99%
“…In this paper, we intend to use DRL-based A3C algorithm [25] to explore unknown environments, where GME goes through different task offloading decisions and UAVs learn from feedback by trying different moves. Continuously, the global network optimizes task offloading decisions and location moves until a suboptimal solution is obtained.…”
Section: Proposed Drl-based Approach: A3cmentioning
confidence: 99%