Matching Items (5)

154975-Thumbnail Image.png

An investigation of topics in model-lite planning and multi-agent planning

Description

Automated planning addresses the problem of generating a sequence of actions that enable a set of agents to achieve their goals.This work investigates two important topics from the field of

Automated planning addresses the problem of generating a sequence of actions that enable a set of agents to achieve their goals.This work investigates two important topics from the field of automated planning, namely model-lite planning and multi-agent planning. For model-lite planning, I focus on a prominent model named Annotated PDDL and it's related application of robust planning. For this model, I try to identify a method of leveraging additional domain information (available in the form of successful plan traces). I use this information to refine the set of possible domains to generate more robust plans (as compared to the original planner) for any given problem. This method also provides us a way of overcoming one of the major drawbacks of the original approach, namely the need for a domain writer to explicitly identify the annotations.

For the second topic, the central question I ask is ``{\em under what conditions are multiple agents actually needed to solve a given planning problem?}''. To answer this question, the multi-agent planning (MAP) problem is classified into several sub-classes and I identify the conditions in each of these sub-classes that can lead to required cooperation (RC). I also identify certain sub-classes of multi-agent planning problems (named DVC-RC problems), where the problems can be simplified using a single virtual agent. This insight is later used to propose a new planner designed to solve problems from these subclasses. Evaluation of this new planner on all the current multi-agent planning benchmarks reveals that most current multi-agent planning benchmarks only belong to a small subset of possible classes of multi-agent planning problems.

Contributors

Agent

Created

Date Created
  • 2016

150555-Thumbnail Image.png

Modeling frameworks for supply chain analytics

Description

Supply chains are increasingly complex as companies branch out into newer products and markets. In many cases, multiple products with moderate differences in performance and price compete for the same

Supply chains are increasingly complex as companies branch out into newer products and markets. In many cases, multiple products with moderate differences in performance and price compete for the same unit of demand. Simultaneous occurrences of multiple scenarios (competitive, disruptive, regulatory, economic, etc.), coupled with business decisions (pricing, product introduction, etc.) can drastically change demand structures within a short period of time. Furthermore, product obsolescence and cannibalization are real concerns due to short product life cycles. Analytical tools that can handle this complexity are important to quantify the impact of business scenarios/decisions on supply chain performance. Traditional analysis methods struggle in this environment of large, complex datasets with hundreds of features becoming the norm in supply chains. We present an empirical analysis framework termed Scenario Trees that provides a novel representation for impulse and delayed scenario events and a direction for modeling multivariate constrained responses. Amongst potential learners, supervised learners and feature extraction strategies based on tree-based ensembles are employed to extract the most impactful scenarios and predict their outcome on metrics at different product hierarchies. These models are able to provide accurate predictions in modeling environments characterized by incomplete datasets due to product substitution, missing values, outliers, redundant features, mixed variables and nonlinear interaction effects. Graphical model summaries are generated to aid model understanding. Models in complex environments benefit from feature selection methods that extract non-redundant feature subsets from the data. Additional model simplification can be achieved by extracting specific levels/values that contribute to variable importance. We propose and evaluate new analytical methods to address this problem of feature value selection and study their comparative performance using simulated datasets. We show that supply chain surveillance can be structured as a feature value selection problem. For situations such as new product introduction, a bottom-up approach to scenario analysis is designed using an agent-based simulation and data mining framework. This simulation engine envelopes utility theory, discrete choice models and diffusion theory and acts as a test bed for enacting different business scenarios. We demonstrate the use of machine learning algorithms to analyze scenarios and generate graphical summaries to aid decision making.

Contributors

Agent

Created

Date Created
  • 2012

150284-Thumbnail Image.png

FLOSSSim: understanding the Free/Libre Open Source Software (FLOSS) development process through agent-based modeling

Description

Free/Libre Open Source Software (FLOSS) is the product of volunteers collaborating to build software in an open, public manner. The large number of FLOSS projects, combined with the data that

Free/Libre Open Source Software (FLOSS) is the product of volunteers collaborating to build software in an open, public manner. The large number of FLOSS projects, combined with the data that is inherently archived with this online process, make studying this phenomenon attractive. Some FLOSS projects are very functional, well-known, and successful, such as Linux, the Apache Web Server, and Firefox. However, for every successful FLOSS project there are 100's of projects that are unsuccessful. These projects fail to attract sufficient interest from developers and users and become inactive or abandoned before useful functionality is achieved. The goal of this research is to better understand the open source development process and gain insight into why some FLOSS projects succeed while others fail. This dissertation presents an agent-based model of the FLOSS development process. The model is built around the concept that projects must manage to attract contributions from a limited pool of participants in order to progress. In the model developer and user agents select from a landscape of competing FLOSS projects based on perceived utility. Via the selections that are made and subsequent contributions, some projects are propelled to success while others remain stagnant and inactive. Findings from a diverse set of empirical studies of FLOSS projects are used to formulate the model, which is then calibrated on empirical data from multiple sources of public FLOSS data. The model is able to reproduce key characteristics observed in the FLOSS domain and is capable of making accurate predictions. The model is used to gain a better understanding of the FLOSS development process, including what it means for FLOSS projects to be successful and what conditions increase the probability of project success. It is shown that FLOSS is a producer-driven process, and project factors that are important for developers selecting projects are identified. In addition, it is shown that projects are sensitive to when core developers make contributions, and the exhibited bandwagon effects mean that some projects will be successful regardless of competing projects. Recommendations for improving software engineering in general based on the positive characteristics of FLOSS are also presented.

Contributors

Agent

Created

Date Created
  • 2011

150062-Thumbnail Image.png

TaxiWorld: developing and evaluating solution methods for multi-agent planning domains

Description

TaxiWorld is a Matlab simulation of a city with a fleet of taxis which operate within it, with the goal of transporting passengers to their destinations. The size of the

TaxiWorld is a Matlab simulation of a city with a fleet of taxis which operate within it, with the goal of transporting passengers to their destinations. The size of the city, as well as the number of available taxis and the frequency and general locations of fare appearances can all be set on a scenario-by-scenario basis. The taxis must attempt to service the fares as quickly as possible, by picking each one up and carrying it to its drop-off location. The TaxiWorld scenario is formally modeled using both Decentralized Partially-Observable Markov Decision Processes (Dec-POMDPs) and Multi-agent Markov Decision Processes (MMDPs). The purpose of developing formal models is to learn how to build and use formal Markov models, such as can be given to planners to solve for optimal policies in problem domains. However, finding optimal solutions for Dec-POMDPs is NEXP-Complete, so an empirical algorithm was also developed as an improvement to the method already in use on the simulator, and the methods were compared in identical scenarios to determine which is more effective. The empirical method is of course not optimal - rather, it attempts to simply account for some of the most important factors to achieve an acceptable level of effectiveness while still retaining a reasonable level of computational complexity for online solving.

Contributors

Agent

Created

Date Created
  • 2011

156782-Thumbnail Image.png

Complexity studies of firm dynamics

Description

This thesis consists of three projects employing complexity economics methods to explore firm dynamics. The first is the Firm Ecosystem Model, which addresses the institutional conditions of capital access and

This thesis consists of three projects employing complexity economics methods to explore firm dynamics. The first is the Firm Ecosystem Model, which addresses the institutional conditions of capital access and entrenched competitive advantage. Larger firms will be more competitive than smaller firms due to efficiencies of scale, but the persistence of larger firms is also supported institutionally through mechanisms such as tax policy, capital access mechanisms and industry-favorable legislation. At the same time, evidence suggests that small firms innovate more than larger firms, and an aggressive firm-as-value perspective incentivizes early investment in new firms in an attempt to capture that value. The Ecological Firm Model explores the effects of the differences in innovation and investment patterns and persistence rates between large and small firms.

The second project is the Structural Inertia Model, which is intended to build theory around why larger firms may be less successful in capturing new marketshare than smaller firms, as well as to advance fitness landscape methods. The model explores the possibility that firms with larger scopes may be less effective in mitigating the costs of cooperation because conditions may arise that cause intrafirm conflicts. The model is implemented on structured fitness landscapes derived using the maximal order of interaction (NM) formulation and described using local optima networks (LONs), thus integrating these novel techniques.

Finally, firm dynamics can serve as a proxy for the ease at which people can voluntarily enter into the legal cooperative agreements that constitute firms. The third project, the Emergent Firm model, is an exploration of how this dynamic of voluntary association may be affected by differing capital institutions, and explores the macroeconomic implications of the economies that emerge out of the various resulting firm populations.

Contributors

Agent

Created

Date Created
  • 2018