Semisupervised Deep Reinforcement Learning in Support of IoT and Smart City Services
Citations
1,153 citations
Cites background from "Semisupervised Deep Reinforcement L..."
...Then, the authors in [181] introduce the semi-supervised DRL framework that utilizes variational auto-encoders [182] as an inference engine to infer the classification of unlabeled data....
[...]
975 citations
Cites background from "Semisupervised Deep Reinforcement L..."
...In particular, their framework envisions a virtual agent in indoor environments [319], which can constantly receive state information during training, including signal strength indicators, current agent location, and the real (labeled data) and inferred (via a VAE) distance to the target....
[...]
903 citations
411 citations
Cites background from "Semisupervised Deep Reinforcement L..."
...) across centralized and distributed cloud computing frameworks, utilizing IoT devices and some novel mechanisms [67], [85], [95], [101], [134], [142], [160]....
[...]
...[95] developed a semi-supervised deep reinforcement learning system to support smart city applications based on both structured and unstructured data....
[...]
407 citations
References
[...]
46,982 citations
37,989 citations
"Semisupervised Deep Reinforcement L..." refers background in this paper
...In this regard, reinforcement learning [11] can be exploited to formulate and solve the problem....
[...]
23,074 citations
"Semisupervised Deep Reinforcement L..." refers background or methods in this paper
...This dataset of recently experienced transitions along with the experience replay mechanism are critical for the integration of reinforcement learning and deep neural networks [39]....
[...]
...In the deep Q-Network approach, we need a deep neural network that approximates the optimal action-value function (Q) [39]...
[...]
10,447 citations
"Semisupervised Deep Reinforcement L..." refers methods in this paper
...The deep neural networks are implemented on Google TensorFlow [41] using the Keras package [42]....
[...]
8,757 citations
"Semisupervised Deep Reinforcement L..." refers methods in this paper
...We develop the theoretical foundation of our method based on [12] and [16]....
[...]
...DRL has been proposed in recent years [12] and is gaining...
[...]
...was demonstrated by Google to achieve high accuracy in the Atari games [12] and is a suitable candidate for the learning process in the IoT applications....
[...]