Search Constraints

Start Over
Filtering by: Creator Beshur, Athena D. Remove constraint Creator: Beshur, Athena D. Academic Affiliation Computer Science Remove constraint Academic Affiliation: Computer Science

Search Results

  • PlanView & HViews : graphical user interfaces for viewing plan data

    Creator:
    Tabayoyon, Al
    Abstract:
    Visualizing and navigating through a plan is difficult without graphics. Two X applications, PlanView and HViews, are graphical user interfaces to an AI planner, OPIE, developed at the University of Oregon. In addition to a plan generator, OPIE includes a facility to generate operator abstractions which in turn are used...
    Resource Type:
    Capstone Project
    Full Text:
    widgets were required. These three widgets are combined with existing Athena Widgets to create two types

  • Average-reward reinforcement learning for product delivery by multiple vehicles

    Creator:
    Tang, Hong
    Abstract:
    Real time delivery of products is the context of stochastic demands and multiple vehicles is a difficult problem as it requires the joint investigation of the problems in inventory control and vehicle routing. We model this problem in the framework of Average reward Reinforcement Learning (ARL) and present experimental results...
    Resource Type:
    Capstone Project
    Full Text:
    distribution center. The action space consists of all these actions for each truck, which means d + l actions

  • A two level minimal perfect hash function for large data sets

    Creator:
    Barrar, Howard
    Abstract:
    Recently several minimal perfect hashing functions far small static word sets have been developed. However, they are limited to sets of 50 words or less. In this paper, a Two Level Minimal Perfect Hash Function for large data sets is given. It partitions a large static set into small sets...
    Resource Type:
    Capstone Project
    Full Text:
    . Step 2 hash es t h e d a ta i n t h e s ma 11 sets. Fig. 1 and 2 present an overview of houi the

  • Hierarchical average reward reinforcement learning

    Creator:
    Seri, Sandeep
    Abstract:
    Reinforcement Learning (RL) is the study of agents that learn optimal behavior by interacting with and receiving rewards and punishments from an unknown environment. RL agents typically do this by learning value functions that assign a value to each state (situation) or to each state-action pair. Recently, there has been...
    Resource Type:
    Masters Thesis

  • Intercom : a development tool for multicomputer-targeted Dataparallel C programs

    Creator:
    McCallum, Darcy
    Resource Type:
    Capstone Project
    Full Text:
    /newdpcl*.dpc Directories jarc4r ,1/.d c/root/ revie1.,.1/ne1.,_1d c/. darc~m/.dpc/mot/preview/newdpcl

  • Active object systems

    Creator:
    Choi, Sungwoon
    Abstract:
    An active object system is a transition-based object-oriented system suitable for the design of various concurrent systems. An AOS consists of a collection of interacting objects, where the behavior of each object is determined by the transition statements provided in the class of that object. A transition statement is a...
    Resource Type:
    Dissertation
    Full Text:
    ., Motif widget set of Open Software Foundation (OSF), the Athena widget set developed at M.I.T, and

  • A study of model-based average reward reinforcement learning

    Creator:
    Ok, DoKyeong
    Abstract:
    Reinforcement Learning (RL) is the study of learning agents that improve their performance from rewards and punishments. Most reinforcement learning methods optimize the discounted total reward received by an agent, while, in many domains, the natural criterion is to optimize the average reward per time step. In this thesis, we...
    Resource Type:
    Dissertation

  • Interactive HTML

    Creator:
    Hackborn, Dianne
    Abstract:
    As the World Wide Web continues to grow, people clearly want to do much more with it than just publish static pages of text and graphics. While such increased interactivity has traditionally been accomplished through the use of server-side CGI scripts, much recent research on Web browsers has been on...
    Resource Type:
    Masters Thesis