• 6 Pages 19-lowerbounds
    19-lowerbounds

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Algorithms Lecture 19: Lower Bounds It was a Game called Yes and No, where Scrooge's nephew had to think of something, and the rest must find out what; he only answering to their questions yes or no, as the case was. The brisk fire of questioning to

  • 3 Pages 16-maxflowalgs
    16-maxflowalgs

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Algorithms Lecture 16: Max-Flow Algorithms and Applications A process cannot be understood by stopping it. Understanding must move with the flow of the process, must join it and flow with it. - The First Law of Mentat, in Frank Herbert's Dune (1965)

  • 17 Pages 21-nphard
    21-nphard

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Algorithms Lecture 21: NP-Hard Problems Math class is tough! - Teen Talk Barbie (1992) That's why I like it! - What she should have said next The wonderful thing about standards is that there are so many of them to choose from. - Grace Hopper If a p

  • 1650 Pages ICML99Bicycle
    ICML99Bicycle

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    %!PS-Adobe-2.0 %Creator: dvips(k) 5.78 Copyright 1998 Radical Eye Software (www.radicaleye.com) %Title: ml99.dvi %Pages: 10 %PageOrder: Ascend %BoundingBox: 0 0 612 792 %EndComments %DVIPSCommandLine: dvips ml99 -o %DVIPSParameters: dpi=1200, compres

  • 3 Pages JRmp2_writeup
    JRmp2_writeup

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Summary of MP2 K Nearest-Neighbor Controller Implementation Josh Rule - CS548 - DeJong - 2009.04.16 1 Implementation As with the previously implemented PID controller, the theory behind K Nearest-Neighbor as a learning algorithm is not difficult.

  • 6 Pages Assignments
    Assignments

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Machine Problem 3: 4/23/09, due: 5/5/09 Write an agent that flies the Pitts to a specific point at a specific heading and hold it straight and level for 500 feet. Again to start things your agent should call FGI.Ready(self) after which it will

  • 6 Pages MP1Red
    MP1Red

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Red Team Report Brian Romanowski Adam Vogel Jason Skowronski Ming-Wei Chang March 2, 2006 1 Introduction We implemented a three-layered control architecture to buzz the tower. At the lowest level, a set of PID controllers handle low level control

  • 4 Pages Assignments
    Assignments

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Machine Problem 2: given 3/30/09, due: 4/16/09 Write a controller that flies the Pitts following a specified circular curvature. Again you will hand in code and a brief paper describing / defending what you did. The code should include any learning

  • 1 Page Expectations
    Expectations

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    CS / ECE 548 CLASS EXPECTATIONS The goal of this course is in part to learn new AI principles and methods and in part to learn how to apply AI techniques in a research setting. Our research topics this semester will be relational learning and pla

  • 2 Pages RelNotes
    RelNotes

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    4/23/06 The MP3 code is now available except for the score function. Four random targets are generated as we discussed between an altitude of 500 and 1500 meters in a square 3000 meters on a side. All four are returned as a succession of four fdm pa

  • 5 Pages PengiArticle
    PengiArticle

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    8u!lapowaJ\9!u8o:>99Z -9.1. ~ estIodEraJ: 9tUf~-J1I8'H '~lq'l!P!p~d woptrnJ ,(u'l! IOJ A1iwJ ~ A(fYlj ~oa II! os pU1! pU'l!StlO'I~ '8 'IuJAom (".19MB 'uo'~'1I~od~oONffi e1{~ ~ou 'Ult1lPun,i ItaQI3S ~uon.N ]0 "tit Jo ~ti9uodmo:) " WI{ saeq el{

  • 6 Pages MP2Red
    MP2Red

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Probabilistic Planning in Aircraft Control via MDPs Adam Vogel, Paul Winward, Ming-Wei Chang Department of Computer Science Abstract In this work we consider the solution of probabilistic-planning tasks with the Markov Decision Process formalism. We

  • 9 Pages Randlov
    Randlov

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    J " ,Learningto Drive a Bicycleusing Reinforcement Learning and Shaping 463 Jette Rand1~v CATS. Niels Bohr Institute. University of Copenhagen. Blegdamsvej17. DK-2100 Copenhagen Denmark 0. randlov@nbi.dk Preben Alstrtfm, alstrom@cats.nbi.dk Abstr

  • 44 Pages BrodieMLJ01
    BrodieMLJ01

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Iterated Phantom Induction: A Knowledge-Based Approach to Learning Control Mark Brodie and Gerald DeJong Department of Computer Science, Beckman Institute University of Illinois at Urbana-Champaign 405 N Mathews Avenue, Urbana, IL 61801 m-brodie@cs.u

  • 7 Pages MP1Green
    MP1Green

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    CS 548 Project 1: Buzz the Tower Lee Chou, Paul Winward, Mike Yin {lchou1,winward,mikeyin2}@uiuc.edu Abstract This project report details our efforts to fly the Fokker airplane in the Flight Gear flight simulator to a certain point near the air contr

  • 14 Pages MP2Green
    MP2Green

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Improving Control in Aircraft Flight using Reinforcement Learning Lee-Ching Chou, Alex Sorokin, Mike Yin, Matt Young Department of Computer Science University of Illinois, Urbana-Champaign Abstract Our goal is to devise an accurate and reliable mode

  • 10 Pages Brodie
    Brodie

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    :I:timL (11 57 Learning to Ride a Bicycle using Iterated Phantom Induction Mark Brodie and Gerald Dejong Department of Computer Science ~JcmAn Institute University of lllinois at Urbana-Champaign Urbana, IL 61801 m-brodieOcs.uiuc.edu and dejongOcs

  • 44 Pages CI99acro
    CI99acro

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    DeJong, G., AI Can Rival Control Theory for Goal Achievement in a Challenging Dynamical System. Computational Intelligence, 1999. 15(4): p. 333-366. AI can Rival Control Theory for Goal Achievement in Some Difficult Dynamical Systems Gerald DeJong

  • 8 Pages MP1Blue
    MP1Blue

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    Abstracting Complex Dynamic Systems Using Cascaded Controllers Alex Sorokin, Alan Fettinger, Matt Young, and Quang Do 2006 Abstract It is difficult to create an agent that directly interacts with a complex world to accomplish goals. We intend to show

  • 8 Pages MP2Blue
    MP2Blue

    School: University Of Illinois, Urbana Champaign

    Course: Models Of Cognitive Processes

    OnLineDynamicWaypointGenerationandFollowing forNonHolonomicRobots {Alan,Brian,Jason,Quang} {fettingr,romanows,skowrons,quangdo2}@uiuc.edu UniversityofIllinois,ChampaignUrbana Abstract.Accomplishinglongtermgoalswithnonholonomicrobotsisa complextask,es

Back to course listings