相关论文: Hierarchical Deep Q-Network from Imperfect Demonst…

The use of target networks is a common practice in deep reinforcement learning for stabilizing the training; however, theoretical understanding of this technique is still limited. In this paper, we study the so-called periodic Q-learning…

Despite the empirical success of the deep Q network (DQN) reinforcement learning algorithm and its variants, DQN is still not well understood and it does not guarantee convergence. In this work, we show that DQN can indeed diverge and cease…

A sophisticated hybrid quantum convolutional neural network (HQCNN) is conceived for handling the pilot assignment task in cell-free massive MIMO systems, while maximizing the total ergodic sum throughput. The existing model-based solutions…

The deep layers of modern neural networks extract a rather rich set of features as an input propagates through the network. This paper sets out to harvest these rich intermediate representations for quantization with minimal accuracy loss…

Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development.…

The rapid advancement of generative artificial intelligence has enabled the creation of highly realistic fake facial images, posing serious threats to personal privacy and the integrity of online information. Existing deepfake detection…

We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a…

Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of…

Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad' in reinforcement learning: bootstrapping, off-policy learning, and function approximation.…

Meshing is a critical, but user-intensive process necessary for stable and accurate simulations in computational fluid dynamics (CFD). Mesh generation is often a bottleneck in CFD pipelines. Adaptive meshing techniques allow the mesh to be…

State-of-the-art deep Q-learning methods update Q-values using state transition tuples sampled from the experience replay buffer. This strategy often uniformly and randomly samples or prioritizes data sampling based on measures such as the…

Hierarchical and complex Mathematical Expression Recognition (MER) is challenging due to multiple possible interpretations of a formula, complicating both parsing and evaluation. In this paper, we introduce the Hierarchical Detail-Focused…

The current deep neural network algorithm still stays in the end-to-end training supervision method like Image-Label pairs, which makes traditional algorithm is difficult to explain the reason for the results, and the prediction logic is…

Knowledge distillation (KD) has demonstrated remarkable success across various domains, but its application to medical imaging tasks, such as kidney and liver tumor segmentation, has encountered challenges. Many existing KD methods are not…

We propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose,…

Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our…

Networked video applications, e.g., video conferencing, often suffer from poor visual quality due to unexpected network fluctuation and limited bandwidth. In this paper, we have developed a Quality Enhancement Network (QENet) to reduce the…

We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value…

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

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…