Related papers: Economic span selection of bridge based on deep re…
Sequential decision tasks with incomplete information are characterized by the exploration problem; namely the trade-off between further exploration for learning more about the environment and immediate exploitation of the accrued…
In many reinforcement learning (RL) problems, it takes some time until a taken action by the agent reaches its maximum effect on the environment and consequently the agent receives the reward corresponding to that action by a delay called…
In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning…
This paper presents a methodology for combining programming and mathematics to optimize elevator wait times. Based on simulated user data generated according to the canonical three-peak model of elevator traffic, we first develop a naive…
Although recent model-free reinforcement learning algorithms have been shown to be capable of mastering complicated decision-making tasks, the sample complexity of these methods has remained a hurdle to utilizing them in many real-world…
In many engineered systems, optimization is used for decision making at time-scales ranging from real-time operation to long-term planning. This process often involves solving similar optimization problems over and over again with slightly…
Deep Q-learning is investigated as an end-to-end solution to estimate the optimal strategies for acting on time series input. Experiments are conducted on two idealized trading games. 1) Univariate: the only input is a wave-like price time…
In this paper, we analyze the effect of a policy recommendation on the performance of an artificial interbank market. Financial institutions stipulate lending agreements following a public recommendation and their individual information.…
Batching has a fundamental influence on the efficiency of deep neural network (DNN) execution. However, for dynamic DNNs, efficient batching is particularly challenging as the dataflow graph varies per input instance. As a result,…
Live fire creates a dynamic, rapidly changing environment that presents a worthy challenge for deep learning and artificial intelligence methodologies to assist firefighters with scene comprehension in maintaining their situational…
Off-Policy reinforcement learning (RL) is an important class of methods for many problem domains, such as robotics, where the cost of collecting data is high and on-policy methods are consequently intractable. Standard methods for applying…
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…
During network planning phase, optimal network planning implemented through efficient resource allocation and static traffic demand provisioning in IP-over-elastic optical network (IP-over-EON) is significantly challenging compared with the…
Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in…
To be effective, efficient, and diverse, deep learning models need to dynamically choose its architecture based on signals from a population of neurons. We hypothesize dynamic routing models can be improved with neural inhibition in those…
This paper concerns automated vehicles negotiating with other vehicles, typically human driven, in crossings with the goal to find a decision algorithm by learning typical behaviors of other vehicles. The vehicle observes distance and speed…
In this paper, we propose a novel deep Q-network (DQN)-based edge selection algorithm designed specifically for real-time surveillance in unmanned aerial vehicle (UAV) networks. The proposed algorithm is designed under the consideration of…
In this work we present a method for using Deep Q-Networks (DQNs) in multi-objective environments. Deep Q-Networks provide remarkable performance in single objective problems learning from high-level visual state representations. However,…
Deep reinforcement learning for high dimensional, hierarchical control tasks usually requires the use of complex neural networks as functional approximators, which can lead to inefficiency, instability and even divergence in the training…
A method based on deep artificial neural networks and empirical risk minimization is developed to calculate the boundary separating the stopping and continuation regions in optimal stopping. The algorithm parameterizes the stopping boundary…