相关论文: Deep Q-Learning with Gradient Target Tracking

In reinforcement learning, it is often difficult to automate high-dimensional, rapid decision-making in dynamic environments, especially when domains require real-time online interaction and adaptive strategies such as web-based games. This…

We apply Deep Q-network (DQN) with the consideration of safety during the task for deciding whether to conduct the maneuver. Furthermore, we design two similar Deep Q learning frameworks with quadratic approximator for deciding how to…

In this paper, we propose a general deep learning training framework XGrad which introduces weight prediction into the popular gradient-based optimizers to boost their convergence and generalization when training the deep neural network…

Stochastic gradient descent (SGD) has been the dominant optimization method for training deep neural networks due to its many desirable properties. One of the more remarkable and least understood quality of SGD is that it generalizes…

Fully quantized training (FQT), which uses low-bitwidth hardware by quantizing the activations, weights, and gradients of a neural network model, is a promising approach to accelerate the training of deep neural networks. One major…

Distribution network reconfiguration (DNR) has proved to be an economical and effective way to improve the reliability of distribution systems. As optimal network configuration depends on system operating states (e.g., loads at each node),…

Tennis strategy optimization is a challenging sequential decision-making problem involving hierarchical scoring, stochastic outcomes, long-horizon credit assignment, physical fatigue, and adaptation to opponent skill. I present a…

Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…

Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignment with the task…

Deep Reinforcement Learning (RL) has considerably advanced over the past decade. At the same time, state-of-the-art RL algorithms require a large computational budget in terms of training time to converge. Recent work has started to…

Quantization techniques applied to the inference of deep neural networks have enabled fast and efficient execution on resource-constraint devices. The success of quantization during inference has motivated the academic community to explore…

This paper introduces a novel deep learning based approach for vision based single target tracking. We address this problem by proposing a network architecture which takes the input video frames and directly computes the tracking score for…

Recent progress on deep learning relies heavily on the quality and efficiency of training algorithms. In this paper, we develop a fast training method motivated by the nonlinear Conjugate Gradient (CG) framework. We propose the Conjugate…

The quantum internet holds transformative potential for global communication by harnessing the principles of quantum information processing. Despite significant advancements in quantum communication technologies, the efficient distribution…

This paper explores a deep reinforcement learning approach applied to the packet routing problem with high-dimensional constraints instigated by dynamic and autonomous communication networks. Our approach is motivated by the fact that…

Real-world reinforcement learning tasks often involve some form of partial observability where the observations only give a partial or noisy view of the true state of the world. Such tasks typically require some form of memory, where the…

Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert…

In this paper, we aim at providing an introduction to the gradient descent based optimization algorithms for learning deep neural network models. Deep learning models involving multiple nonlinear projection layers are very challenging to…

Deep reinforcement learning has been applied more and more widely nowadays, especially in various complex control tasks. Effective exploration for noisy networks is one of the most important issues in deep reinforcement learning. Noisy…

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…