Rapid strides made in the development of computing infrastructure over the last ten years have played a crucial role in significantly advancing the state-of-the-art in reinforcement learning. These developments have enabled the successful implementation of reinforcement learning…
"28" Result
Sort By:
When developing reinforcement learning algorithms, the main issues are dealing with large state spaces and action spaces. For the most part, the state space complexity problem was solved with the advent of AlphaZero. AlphaZero is able to deal with unfathomably large state spaces…
Same-day delivery (SDD) changes the way people shop as it combines immediate product availability and the convenience of ordering from electronic devices. The SDD market has seen a fast growth over the past decade. These services have further gained popularity during the COVID-1…
In many applications in robotics, there exist teams of robots operating in dynamic environments requiring the design of complex communication and control schemes. The problem is made easier if one assumes the presence of an oracle that has instantaneous access to states of all e…
Solving combinatorial optimization problems, especially stochastic problems, could be complicated. Reinforcement learning (RL) algorithms train a machine learning model to make a sequence of decisions. Instead of learning the direct rewards, it learns the long-term effects on th…
Continuous increases in traffic volume and limited available capacity in the roadway system have created a need for improved traffic control. From traditional pre-timed isolated signals to actuated and coordinated corridors, traffic control for urban networks has evolved into mo…
Classical value estimation reinforcement learning algorithms do not perform very well in dynamic environments. On the other hand, the reinforcement learning of animals is quite flexible: they can adapt to dynamic environments very quickly and deal with noisy inputs very effectiv…
Closed-loop optimization deals with problems in which candidate solutions are evaluated by conducting experiments, e.g. physical or biochemical experiments. Although this form of optimization is becoming more popular across the sciences, it may be subject to rather unexplored re…
How can real robots with many degrees of freedom - without previous knowledge of themselves or their environment - act and use the resulting observations to efficiently develop the ability to generate a wide set of useful behaviours? This thesis presents a novel framework that e…
Reinforcement learning occurs when organisms adapt the propensities of given behaviours on the basis of associations with reward and punishment. Currently, reinforcement learning models have been validated in minimalist environments in which only 1-2 environmental stimuli are pr…
This thesis investigates decision-making in two-player imperfect information games against opponents whose actions can affect our rewards, and whose strategies may be based on memories of interaction, or may be changing, or both. The focus is on modelling these dynamic opponents…
This dissertation investigates the use of hierarchy and abstraction as a means of solving complex sequential decision making problems such as those with continuous state and/or continuous action spaces, and domains with multiple cooperative agents. This thesis develops several n…
The notions of collaboration, advantage, cost and impact are investigated in this dissertation, following are the details. Contribution to Cooperation between Agents for Routing in an Unknown Graph Using Reinforcement Learning: First of all this work investigates the cooperation…
We have developed a game-theory based prediction tool, named Preana, based on a promising model developed by Professor Bruce Beuno de Mesquita. The first part of this work is dedicated to exploration of the specifics of Mesquita's algorithm and reproduction of the factors and fe…
The objective of this dissertation is to design decentralized controllers to enhance the transient stability of power systems. Due to the nonlinearities and complexities of the system, nonlinear control design techniques are required to improve its dynamic performance. In this d…
Planning and scheduling are critical operational roles to any manufacturing business. In most companies in the chemical industry, these roles are handled by human planners and schedulers who have to make complex decisions under uncertainty to balance inventory costs, production …
A key question in the cognitive control literature involves determining the executive functions that mediate cognitive flexibility (CF) and the brain regions that support them. Recent perspectives have offered persuasive evidence suggesting that CF may be guided by low-level ass…
Dynamic treatment regimes (DTRs) have gained increasing interest in the field of personalized health care in the last two decades, as they provide a sequence of individualized decision rules for treating patients over time. In a DTR, treatment is adapted in response to the chang…
This dissertation focuses on two different but related natural language processing problems, namely, question answering and question generation. Automated question answering (QA) is the process of finding answers to natural language questions. This problem has been studied since…