Related papers: Deep Q-Learning with Gradient Target Tracking
Most reinforcement learning algorithms implicitly assume strong synchrony. We present novel attacks targeting Q-learning that exploit a vulnerability entailed by this assumption by delaying the reward signal for a limited time period. We…
We present a novel algorithm for training deep neural networks in supervised (classification and regression) and unsupervised (reinforcement learning) scenarios. This algorithm combines the standard stochastic gradient descent and the…
The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic,…
Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at…
Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially…
Knowledge tracing (KT) models, e.g., the deep knowledge tracing (DKT) model, track an individual learner's acquisition of skills over time by examining the learner's performance on questions related to those skills. A practical limitation…
As the third-generation neural networks, Spiking Neural Networks (SNNs) have great potential on neuromorphic hardware because of their high energy-efficiency. However, Deep Spiking Reinforcement Learning (DSRL), i.e., the Reinforcement…
We introduce a novel schema for sequence to sequence learning with a Deep Q-Network (DQN), which decodes the output sequence iteratively. The aim here is to enable the decoder to first tackle easier portions of the sequences, and then turn…
The use of Reinforcement Learning (RL) is still restricted to simulation or to enhance human-operated systems through recommendations. Real-world environments (e.g. industrial robots or power grids) are generally designed with safety…
Communication of model updates between client nodes and the central aggregating server is a major bottleneck in federated learning, especially in bandwidth-limited settings and high-dimensional models. Gradient quantization is an effective…
In this paper, we investigate dynamic resource allocation (DRA) problems for Internet of Things (IoT) in real-time cloud radio access networks (C-RANs), by combining gradient boosting approximation and deep reinforcement learning to solve…
The deadly triad refers to the instability of a reinforcement learning algorithm when it employs off-policy learning, function approximation, and bootstrapping simultaneously. In this paper, we investigate the target network as a tool for…
Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…
We propose a distributed deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is based on the deep Q-network, a convolutional neural network trained…
Deep reinforcement learning includes a broad family of algorithms that parameterise an internal representation, such as a value function or policy, by a deep neural network. Each algorithm optimises its parameters with respect to an…
Deep reinforcement learning policies, despite their outstanding efficiency in simulated visual control tasks, have shown disappointing ability to generalize across disturbances in the input training images. Changes in image statistics or…
This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing…
Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…
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…
This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with…