CMSC 477/677 Agent Architectures and Multi-Agent Systems UMBC Prof. Marie desJardins Spring 2005.

Slides:



Advertisements
Similar presentations
Some questions o What are the appropriate control philosophies for Complex Manufacturing systems? Why????Holonic Manufacturing system o Is Object -Oriented.
Advertisements

Dr Jim Briggs Masterliness Not got an MSc myself; BA DPhil; been teaching masters students for 18 years.
Cleveland State University ESC 720 Research Communications Dissertation Proposals Dan Simon 1.
The Pledge of Allegiance
Allegiance Rap Adapted by Teresa Jennings, Music K-8, Volume 12, Number 1 © 2001 Plank Road Publishing All rights reserved. Used with permission.
The Bill of Rights. Bill of Rights Basics First ten Amendments to the Constitution.
Chapter Learning Objectives
1 NSF Graduate Research Fellowship Program Seminar 2 ©Valorie Troesch 2006.
Supporting the Requirement for Flexibility in Automated Business Processes using Intelligent Agents Stewart Green University of the West of England.
Logistics: –My office hours: T, Th 4-5pm or by appointment –Class Web page:
September1999 Excerpts from: Graduate Studies at UMBC CSEE: How to Succeed Marie desJardins CSEE Department, UMBC Thanks to Anupam.
UMass Lowell Computer Science Advanced Algorithms Computational Geometry Prof. Karen Daniels Spring, 2004 Project.
Math 105: Problem Solving in Mathematics. Course Description This course introduces students to the true nature mathematics, what mathematicians really.
April 13, 2004CS WPI1 CS 562 Advanced SW Engineering General Dynamics, Needham Tuesdays, 3 – 7 pm Instructor: Diane Kramer.
CIE 500D “Introduction to Graduate Research in Constructed Systems” (3) Spring Semester, 2007 Friday, 3:00 – 5:30 pm, 140 Ketter Hall Instructor: George.
BA 378: Accounting Information Systems Instructor: Dr. James R. Coakley.
What it is and what it is used for?.  It is a type of writing by an author who is trying to get something. As a result, it is an extremely persuasive.
CSE 1111 Week 1 CSE 1111 Introduction to Computer Science and Engineering.
PROGRAM LAUNCHING Business Plan Writing ELIB 203.
Computer Network Fundamentals CNT4007C
COMP 875 Machine Learning Methods in Image Analysis.
Welcome to AC122 Payroll Accounting 1. AC122 Payroll Accounting Seminar 1 Jim Eads, CPA, MST, MSF 2.
© Yilmaz “Agent-Directed Simulation – Course Outline” 1 Course Outline Dr. Levent Yilmaz M&SNet: Auburn M&S Laboratory Computer Science &
Lecture 1 Page 1 CS 239, Fall 2010 Introduction CS 239 Advanced Topics in Computer Security Peter Reiher September 23, 2010.
Research Methods and Techniques Lecture 1 Introduction & Paper Review 1 © 2004, J S Sventek, University of Glasgow.
Welcome to MT140 Introduction to Management. Unit 1 Outcomes Describe the skills needed by managers Understand the expectations of the course.
UMBC  CSEE   1 Autonomous Agents and Self Organization.
PROJECT 3: HOW DO WE COMMUNICATE Agenda  Today the goal is simple—figure out your topic for paper 3. Here is the plan to make that happen. 
Understanding the Academic Structure of the US Classroom: Syllabus.
What is a Value? What does value mean in math class?
Math 105: Problem Solving in Mathematics
CMSC 491M/691M Agent Architectures and Multi-Agent Systems UMBC Prof. Marie desJardins Spring 2003.
CMSC 691M Agent Architectures & Multi- Agent Systems UMBC Prof. Marie desJardins Spring 2002.
ITEC0700/ NETE0501/ ISEC0502 Research Methodology#2 Suronapee Phoomvuthisarn, Ph.D.
Intro1 1 CIS541 - Software Engineering Project II Dr. David A. Gustafson
Welcome to MT140 Introduction to Management Karen Foreman.
Advanced Legal Writing Seminar: Wednesdays, 10:00 p.m. EST Office Hours: Mondays from 3 – 5 p.m. EST, and by appointment AIM sign-in: cssouthall
CS-112 Object Oriented Concepts Course Syllabus. Outline  Instructor and Prerequisites  What this course is  Learning outcomes  Degree program outcomes.
ECE791 Senior Design Experience Project Requirements and Timeline.
CM220 College Composition II Friday, January 29, Unit 1: Introduction to Effective Academic and Professional Writing Unit 1 Lori Martindale, Instructor.
Multi-Agent Systems: Overview and Research Directions CMSC 671 – Class #26 December 1, 2005 Prof. Marie desJardins.
OS 432 Org Policy and Strategy Clarkson University School of Business Spring 2004 Mike Wasserman Mon 3/08/04 Business Level Strategy II.
Marzano’s Teacher Evaluation Model Marzano is an educational researcher who has developed a teacher evaluation model that has been adopted by most of the.
Computer Networks CNT5106C
Multi-Agent Systems: Overview and Research Directions CMSC 471 March 11, 2014 Prof. Marie desJardins.
CMSC 477/677 Agent Architectures and Multi-Agent Systems UMBC Prof. Marie desJardins Spring 2007.
Part II – Chapters 6 and beyond…. Reliability, Validity, & Grading.
The Pledge of Allegiance Pledge of Allegiance Video.
1 Sobah Abbas Petersen Adjunct Associate Professor, NTNU Researcher, Sintef TDT4252 Modelling of Information Systems Advanced Course TDT4252,
LECTURER-TASNUVA CHAUDHURY (TCY) TERM PROJECT SPRING’16 MGT 321: Organizational Behavior.
Towards the greening of our minds: Green and sustainable chemistry Dr. Anne Marteel-Parrish Assistant Professor of Chemistry.
HCA 311 Entire Course For more classes visit HCA 311 Week 1 DQ 1 Senate vs. House HCA 311 Week 1 DQ 2 Government Revenue HCA 311 Week.
FNA/Spring CENG 562 – Machine Learning. FNA/Spring Contact information Instructor: Dr. Ferda N. Alpaslan
Course Overview Robotics in Construction Automation Instructor Prof. Shih-Chung Kang 2008 Spring.
MGT 415 Entire Course (Ash) FOR MORE CLASSES VISIT MGT 415 Week 1 DQ 1 Organizational Design MGT 415 Week 1 DQ 2 The Research Project.
EEL 5937 Multi Agent Systems -an introduction-. EEL 5937 Content What is an agent? Communication Ontologies Mobility Mutability Applications.
Cynthia Cherry Welcome to AB 140 Unit 1 – Introduction to Management.
EEL 5937 Multi Agent Systems -an introduction-. EEL 5937 Content What is an agent? Communication Ontologies Mobility Mutability Applications.
Pledge of Allegiance.
Autonomous Agents and Self Organization
Chapter 10 Understanding Work Teams
L – Modeling and Simulating Social Systems with MATLAB
The Pledge of Allegiance
HCA 311 Competitive Success/snaptutorial.com
SPE 544 Become Exceptional/ newtonhelp.com. SPE 544 Week 1 Individual Assignment Reflective Paper For more course tutorials visit Based.
The Pledge of Allegiance
Multi-Agent Systems: Overview and Research Directions
Course Guide CSC1201 Computer programming 2.
Computer Networks CNT5106C
Professor: Peter Stone
Presentation transcript:

CMSC 477/677 Agent Architectures and Multi-Agent Systems UMBC Prof. Marie desJardins Spring 2005

Course information Prof desJardins  ITE 337, x53967, Class mailing list   To subscribe, send to with the line: subscribe agents-class Your Name

Today’s overview Class structure and policies What’s an agent? Agent exercise Next class

Class structure: Syllabus Course page:

Class structure: 477 vs. 677 Slightly different weights for assignments Two problem sets for graduate students Agent architectures project: Graduate students must do a more in-depth analysis, relating their findings to the research literature MAS project: Graduate students must include an experimental research component, and submit a research design In general, graduate students are expected to show greater depth in their analysis and synthesis of ideas

Class structure: Participation This is a discussion class  Reading must be done in advance  Participation counts—a lot 40/35% of grade is related to class participation  Class discussion (30/25%) Do you attend class? Are you prepared? Have you done the reading? Have you thought about the discussion questions? Do you contribute to the discussion with insightful questions and comments?  Paper summaries (5%)  Discussion leaders (5%)

Class structure: Agent architecture project Agent architecture project: 20/15% of grade  Download one of the architectures we learn about  Apply the architecture to a domain of your choice Deadlines:  Proposal due Feb. 17 (5% of project grade)  Report due Mar. 17 (70% of grade)  Demonstration week of Mar. 14 (25% of grade)

Class structure: MAS paper/presentation MAS paper/presentation: 25% of grade  Students will select a topic to study in greater depth, write a paper, and give a presentation on that topic. 477: can focus primarily on one or two recent research papers 677: can focus on one or two main papers, but should also include a bibliography of 5-10 (more is OK) papers on the topic, and a significant discussion/analysis of the work in that area.  Proposal and bibliography due Apr. 12 (10% of project grade)  Draft report due May 5 (5%)  Presentation on May 3, 5, 10, 12(?), or 19 (20%) additional days if needed: May 13 and/or May 6  Final report due May 19 (65%) Paper review (of another student’s paper): 5% of grade

MAS competition Multi-agent game (trading agents?) project: 10% of grade  In-class competition – probably May 12  Short report describing design and performance of agent

Policies Grading and academic honesty Plagiarism, citations

Original passage:  I pledge allegiance to the flag of the United States of America, and to the republic for which it stands, one nation, indivisible, with liberty and justice for all. Unacceptable summary:  I promise loyalty to the United States flag, and to the country for which it stands, one nation, with freedom and fairness for all. Plagiarism exercise

Plagiarism exercise II Original passage:  I pledge allegiance to the flag of the United States of America, and to the republic for which it stands, one nation, indivisible, with liberty and justice for all. Acceptable summary:  I promise to be loyal to the United States flag and to the USA itself: One united country that provides basic rights such as liberty and justice to all citizens.

What’s an agent? Weiss, p. 29 [after Wooldridge and Jennings]:  “An agent is a computer system that is situated in some environment, and that is capable of autonomous action in this environment in order to meet its design objectives.” Russell and Norvig, p. 7:  “An agent is just something that perceives and acts.” Rosenschein and Zlotkin, p. 4:  “The more complex the considerations that [a] machine takes into account, the more justified we are in considering our computer an ‘agent,’ who acts as our surrogate in an automated encounter.”

What’s an agent? II Ferber, p. 9:  “An agent is a physical or virtual entity a) Which is capable of acting in an environment, b) Which can communicate directly with other agents, c) Which is driven by a set of tendencies…, d) Which possesses resources of its own, e) Which is capable of perceiving its environment…, f) Which has only a partial representation of this environment…, g) Which possesses skills and can offer services, h) Which may be able to reproduce itself, i) Whose behavior tends towards satisfying its objectives, taking account of the resources and skills available to it and depending on its perception, its representations and the communications it receives.”

OK, so what’s an environment? Isn’t any system that has inputs and outputs situated in an environment of sorts?

What’s autonomy, anyway? Jennings and Wooldridge, p. 4:  “[In contrast with objects, we] think of agents as encapsulating behavior, in addition to state. An object does not encapsulate behavior: it has no control over the execution of methods – if an object x invokes a method m on an object y, then y has no control over whether m is executed or not – it just is. In this sense, object y is not autonomous, as it has no control over its own actions…. Because of this distinction, we do not think of agents as invoking methods (actions) on agents – rather, we tend to think of them requesting actions to be performed. The decision about whether to act upon the request lies with the recipient.” Is an if-then-else statement sufficient to create autonomy?

So now what? If those definitions aren’t useful, is there a useful definition? Should we bother trying to create “agents” at all?

Next class Reading: Wooldridge Chapter 1; Wooldridge & Jennings 1995 Overview by Dr. dJ Tuesday reading: Wooldridge Chapter 3; Levesque et al Discussion leaders!

Multi-agent exercise Getting to know you... getting to know all about you... (or at least your capabilities...)

After-action review or post-mortem, as the case may be… What was the task completion rate? How many agents participated in successful teams? Who was more successful – agents who led teams, or agents who participated on teams? Any particularly successful (or unsuccessful) strategies for forming teams? What’s hard about this problem?