Physical Sciences and Mathematics Commons^™

A Structured Narrative Prompt For Prompting Narratives From Large Language Models: Sentiment Assessment Of Chatgpt-Generated Narratives And Real Tweets, Christopher J. Lynch, Erik J. Jensen, Virginia Zamponi, Kevin O'Brien, Erika Frydenlund, Ross Gore

VMASC Publications

Large language models (LLMs) excel in providing natural language responses that sound authoritative, reflect knowledge of the context area, and can present from a range of varied perspectives. Agent-based models and simulations consist of simulated agents that interact within a simulated environment to explore societal, social, and ethical, among other, problems. Simulated agents generate large volumes of data and discerning useful and relevant content is an onerous task. LLMs can help in communicating agents' perspectives on key life events by providing natural language narratives. However, these narratives should be factual, transparent, and reproducible. Therefore, we present a structured narrative prompt …

A Logistic Regression And Linear Programming Approach For Multi-Skill Staffing Optimization In Call Centers, Thuy Anh Ta, Tien Mai, Fabian Bastin, Pierre L'Ecuyer

Research Collection School Of Computing and Information Systems

We study a staffing optimization problem in multi-skill call centers. The objective is to minimize the total cost of agents under some quality of service (QoS) constraints. The key challenge lies in the fact that the QoS functions have no closed-form and need to be approximated by simulation. In this paper we propose a new way to approximate the QoS functions by logistic functions and design a new algorithm that combines logistic regression, cut generations and logistic-based local search to efficiently find good staffing solutions. We report computational results using examples up to 65 call types and 89 agent groups …

A Monte Carlo Framework For Incremental Improvement Of Simulation Fidelity, Damian Lyons, James Finocchiaro, Misha Novitsky, Chris Korpela

Faculty Publications

Robot software developed in simulation often does not be- have as expected when deployed because the simulation does not sufficiently represent reality - this is sometimes called the `reality gap' problem. We propose a novel algorithm to address the reality gap by injecting real-world experience into the simulation. It is assumed that the robot program (control policy) is developed using simulation, but subsequently deployed on a real system, and that the program includes a performance objective monitor procedure with scalar output. The proposed approach collects simulation and real world observations and builds conditional probability functions. These are used to generate …

Optimization Of Orbital Trajectories Using Neuroevolution Of Augmenting Topologies, Nathan Wetherell

University Scholar Projects

This project aims to determine the feasibility of using NeuroEvolution of Augmenting Topologies (NEAT), an advanced neural network evolution scheme, to optimize orbital transfer trajectories. More specifically, this project compares a genetically evolved neural network to a standard Hohmann transfer between Earth and Mars. To test these two methods, an N-body simulation environment was created to accurately determine the result of gravitational interactions on a theoretical spacecraft when combined with planned engine burns. Once created, this simulation environment was used to train the neural networks created using the NEAT Python module. A genetic algorithm was used to modify the topology …

Deeply Learning Deep Inelastic Scattering Kinematics, Markus Diefenthaler, Abdullah Farhat, Andrii Verbytskyi, Yuesheng Xu

Mathematics & Statistics Faculty Publications

We study the use of deep learning techniques to reconstruct the kinematics of the neutral current deep inelastic scattering (DIS) process in electron–proton collisions. In particular, we use simulated data from the ZEUS experiment at the HERA accelerator facility, and train deep neural networks to reconstruct the kinematic variables Q² and x. Our approach is based on the information used in the classical construction methods, the measurements of the scattered lepton, and the hadronic final state in the detector, but is enhanced through correlations and patterns revealed with the simulated data sets. We show that, with the appropriate selection …

Evaluating Driving Performance Of A Novel Behavior Planning Model On Connected Autonomous Vehicles, Keyur Shah

Honors Scholar Theses

Many current algorithms and approaches in autonomous driving attempt to solve the "trajectory generation" or "trajectory following” problems: given a target behavior (e.g. stay in the current lane at the speed limit or change lane), what trajectory should the vehicle follow, and what inputs should the driving agent apply to the throttle and brake to achieve this trajectory? In this work, we instead focus on the “behavior planning” problem—specifically, should an autonomous vehicle change lane or keep lane given the current state of the system?

In addition, current theory mainly focuses on single-vehicle systems, where vehicles do not communicate with …

Personal Universes: A Solution To The Multi-Agent Value Alignment Problem, Roman V. Yampolskiy

Faculty Scholarship

AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of challenges including personal value extraction, multi-agent value merger and finally in-silico encoding. State-of-the-art research in value alignment shows difficulties in every stage in this process, but merger of incompatible preferences is a particularly difficult challenge to overcome. In this paper we assume that the value extraction problem will be solved and propose a possible way to implement an AI solution which optimally aligns with individual preferences of each user. We conclude by analyzing benefits and limitations of the proposed approach.

Multiagent Coalition Formation In Uncertain Environments With Type-Changing Influences And Its Application Towards Forming Human Coalitions, Nobel A. Khandaker

Department of Computer Science and Engineering: Dissertations, Theses, and Student Research

We aim to solve the problem forming multiagent coalitions in uncertain environments where the coalition members’ capability of solving tasks change due to their learning. The MCFP-Mproblem for the agents refers to forming or joining coalitions on behalf of a set of human users so that those human users can solve tasks and improve their types (expertise) to improve their performances over time. MCFP-A problem for a set of agents refers to their forming or joining coalitions so that they are able to solve a set of assigned tasks while optimize their performance over time. We propose the Integrated Human …