Related papers: An FPGA-Based On-Device Reinforcement Learning App…
In this paper, we study a Deep Reinforcement Learning (DRL) based framework for an online end-user service provisioning in a Network Function Virtualization (NFV)-enabled network. We formulate an optimization problem aiming to minimize the…
Developing deep learning models for resource-constrained Internet-of-Things (IoT) devices is challenging, as it is difficult to achieve both good quality of results (QoR), such as DNN model inference accuracy, and quality of service (QoS),…
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural…
While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to…
Reinforcement Learning (RL) approaches are lately deployed for orchestrating wireless communications empowered by Reconfigurable Intelligent Surfaces (RISs), leveraging their online optimization capabilities. Most commonly, in RL-based…
Backpropagation has been the cornerstone of neural network training for decades, yet its inefficiencies in time and energy consumption limit its suitability for resource-constrained edge devices. While low-precision neural network…
Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on…
The deep neural network (DNN) based AI applications on the edge require both low-cost computing platforms and high-quality services. However, the limited memory, computing resources, and power budget of the edge devices constrain the…
Present-day Deep Reinforcement Learning (RL) systems show great promise towards building intelligent agents surpassing human-level performance. However, the computational complexity associated with the underlying deep neural networks (DNNs)…
Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks. Meanwhile, there have been efforts to adapt transformers to visual tasks…
We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL…
Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The…
In this paper, cooperative edge caching problem is studied in fog radio access networks (F-RANs). Given the non-deterministic polynomial hard (NP-hard) property of the problem, a dueling deep Q network (Dueling DQN) based caching update…
Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge…
In the realm of efficient on-device learning under extreme memory and computation constraints, a significant gap in successful approaches persists. Although considerable effort has been devoted to efficient inference, the main obstacle to…
Deep Reinforcement Learning has shown excellent performance in generating efficient solutions for complex tasks. However, its efficacy is often limited by static training modes and heavy reliance on vast data from stable environments. To…
Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…
The research on deep reinforcement learning which estimates Q-value by deep learning has been attracted the interest of researchers recently. In deep reinforcement learning, it is important to efficiently learn the experiences that an agent…
We analyze the DQN reinforcement learning algorithm as a stochastic approximation scheme using the o.d.e. (for 'ordinary differential equation') approach and point out certain theoretical issues. We then propose a modified scheme called…
Quantization of Deep Neural Network (DNN) activations is a commonly used technique to reduce compute and memory demands during DNN inference, which can be particularly beneficial on resource-constrained devices. To achieve high accuracy,…