Introduction to AI & Intelligent Agents

Similar documents
Intelligent Agents. Chapter 2. Chapter 2 1

Chapter 2. Intelligent Agents. Outline. Agents and environments. Rationality. PEAS (Performance measure, Environment, Actuators, Sensors)

Agents and environments. Intelligent Agents. Reminders. Vacuum-cleaner world. Outline. A vacuum-cleaner agent. Chapter 2 Actuators

Module 12. Machine Learning. Version 2 CSE IIT, Kharagpur

Lecture 10: Reinforcement Learning

LEGO MINDSTORMS Education EV3 Coding Activities

Rover Races Grades: 3-5 Prep Time: ~45 Minutes Lesson Time: ~105 minutes

Reinforcement Learning by Comparing Immediate Reward

SAM - Sensors, Actuators and Microcontrollers in Mobile Robots

Computers Change the World

Designing Autonomous Robot Systems - Evaluation of the R3-COP Decision Support System Approach

Executive Guide to Simulation for Health

THE VIRTUAL WELDING REVOLUTION HAS ARRIVED... AND IT S ON THE MOVE!

Computer Science 141: Computing Hardware Course Information Fall 2012

Axiom 2013 Team Description Paper

MYCIN. The MYCIN Task

Lecture 1: Basic Concepts of Machine Learning

University of Groningen. Systemen, planning, netwerken Bosman, Aart

Class Meeting Time and Place: Section 3: MTWF10:00-10:50 TILT 221

On Human Computer Interaction, HCI. Dr. Saif al Zahir Electrical and Computer Engineering Department UBC

Seminar - Organic Computing

Modeling user preferences and norms in context-aware systems

Robot manipulations and development of spatial imagery

An Introduction to Simio for Beginners

A MULTI-AGENT SYSTEM FOR A DISTANCE SUPPORT IN EDUCATIONAL ROBOTICS

Evidence for Reliability, Validity and Learning Effectiveness

IAT 888: Metacreation Machines endowed with creative behavior. Philippe Pasquier Office 565 (floor 14)

Evolution of Collective Commitment during Teamwork

Multidisciplinary Engineering Systems 2 nd and 3rd Year College-Wide Courses

ISFA2008U_120 A SCHEDULING REINFORCEMENT LEARNING ALGORITHM

AGENDA LEARNING THEORIES LEARNING THEORIES. Advanced Learning Theories 2/22/2016

What s in Your Communication Toolbox? COMMUNICATION TOOLBOX. verse clinical scenarios to bolster clinical outcomes: 1

A student diagnosing and evaluation system for laboratory-based academic exercises

Intensive English Program Southwest College

Laboratorio di Intelligenza Artificiale e Robotica

A systems engineering laboratory in the context of the Bologna Process

DEVELOPMENT OF AN INTELLIGENT MAINTENANCE SYSTEM FOR ELECTRONIC VALVES

Innovative Methods for Teaching Engineering Courses

Math 1313 Section 2.1 Example 2: Given the following Linear Program, Determine the vertices of the feasible set. Subject to:

Consultation skills teaching in primary care TEACHING CONSULTING SKILLS * * * * INTRODUCTION

What is PDE? Research Report. Paul Nichols

Action Models and their Induction

SOFTWARE EVALUATION TOOL

EDEXCEL NATIONALS UNIT 25 PROGRAMMABLE LOGIC CONTROLLERS. ASSIGNMENT No.1 SELECTION CRITERIA

AC : DESIGNING AN UNDERGRADUATE ROBOTICS ENGINEERING CURRICULUM: UNIFIED ROBOTICS I AND II

Speeding Up Reinforcement Learning with Behavior Transfer

Thesis-Proposal Outline/Template

EL RODEO SCHOOL VOLUNTEER HANDBOOK

Introduction to Simulation

UC Merced Proceedings of the Annual Meeting of the Cognitive Science Society

Guru: A Computer Tutor that Models Expert Human Tutors

Software Maintenance

Medical College of Wisconsin and Froedtert Hospital CONSENT TO PARTICIPATE IN RESEARCH. Name of Study Subject:

AMULTIAGENT system [1] can be defined as a group of

Laboratorio di Intelligenza Artificiale e Robotica

Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for

Cognitive Thinking Style Sample Report

Specification and Evaluation of Machine Translation Toy Systems - Criteria for laboratory assignments

Group A Lecture 1. Future suite of learning resources. How will these be created?

A Context-Driven Use Case Creation Process for Specifying Automotive Driver Assistance Systems

Copyright Corwin 2015

MASTER S COURSES FASHION START-UP

RESEARCH UNITS, CENTRES AND INSTITUTES. Annual Report Template

SARDNET: A Self-Organizing Feature Map for Sequences

A Practical Approach to Embedded Systems Engineering Workforce Development

IT Students Workshop within Strategic Partnership of Leibniz University and Peter the Great St. Petersburg Polytechnic University

Life Imitates Lit: A Road Trip to Cultural Understanding. Dr. Patricia Hamilton, Department of English

Computer Science. Embedded systems today. Microcontroller MCR

PELLISSIPPI STATE TECHNICAL COMMUNITY COLLEGE MASTER SYLLABUS APPLIED MECHANICS MET 2025

BPS Information and Digital Literacy Goals

Bachelor Class

Tutoring First-Year Writing Students at UNM

Courses in English. Application Development Technology. Artificial Intelligence. 2017/18 Spring Semester. Database access

Value Creation Through! Integration Workshop! Value Stream Analysis and Mapping for PD! January 31, 2002!

Wright Middle School. School Supplement to the District Policy Guide

Welcome to the session on ACCUPLACER Policy Development. This session will touch upon common policy decisions an institution may encounter during the

Software Development: Programming Paradigms (SCQF level 8)

Lecture 1: Machine Learning Basics

Designing a Computer to Play Nim: A Mini-Capstone Project in Digital Design I

Curriculum Vitae FARES FRAIJ, Ph.D. Lecturer

Managing Sustainable Operations MGMT 410 Bachelor of Business Administration (Sustainable Business Practices) Business Administration Program

Constructing Blank Cloth Dolls to Assess Sewing Skills: A Service Learning Project

CNS 18 21th Communications and Networking Simulation Symposium

The Political Engagement Activity Student Guide

Targetsim Toolbox. Business Board Simulations: Features, Value, Impact. Dr. Gudrun G. Vogt Targetsim Founder & Managing Partner

Author: Justyna Kowalczys Stowarzyszenie Angielski w Medycynie (PL) Feb 2015

A Case-Based Approach To Imitation Learning in Robotic Agents

MISSISSIPPI STATE UNIVERSITY SUG FACULTY SALARY DATA BY COLLEGE BY DISCIPLINE

A. Permission. All students must have the permission of their parent or guardian to participate in any field trip.

21 st Century Skills and New Models of Assessment for a Global Workplace

The One Minute Preceptor: 5 Microskills for One-On-One Teaching

University of Alabama in Huntsville

Journal title ISSN Full text from

Economics 201 Principles of Microeconomics Fall 2010 MWF 10:00 10:50am 160 Bryan Building

High-level Reinforcement Learning in Strategy Games

SYSTEM ENTITY STRUCTUURE ONTOLOGICAL DATA FUSION PROCESS INTEGRAGTED WITH C2 SYSTEMS

Hayward Unified School District Community Meeting #2 at

PATROL OFFICER CQB. A u n i q u e C Q B c o u r s e f o r P o l i c e p e r s o n a l o n l y.

The Enterprise Knowledge Portal: The Concept

STANDARDS AND RUBRICS FOR SCHOOL IMPROVEMENT 2005 REVISED EDITION

Transcription:

Introduction to AI & Intelligent Agents This Lecture Chapters 1 and 2 Next Lecture Chapter 3.1 to 3.4 (Please read lecture topic material before and after each lecture on that topic)

What is Artificial Intelligence? Thought processes vs. behavior Human-like vs. rational-like How to simulate humans intellect and behavior by a machine. Mathematical problems (puzzles, games, theorems) Common-sense reasoning Expert knowledge: lawyers, medicine, diagnosis Social behavior Web and online intelligence Planning for assembly and logistics operations Things we call intelligent if done by a human.

What is AI? Views of AI fall into four categories: Thinking humanly Acting humanly Thinking rationally Acting rationally The textbook advocates "acting rationally

What is Artificial Intelligence (John McCarthy, Basic Questions) What is artificial intelligence? It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable. Yes, but what is intelligence? Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and degrees of intelligence occur in people, many animals and some machines. Isn't there a solid definition of intelligence that doesn't depend on relating it to human intelligence? Not yet. The problem is that we cannot yet characterize in general what kinds of computational procedures we want to call intelligent. We understand some of the mechanisms of intelligence and not others. More in: http://www-formal.stanford.edu/jmc/whatisai/node1.html

Thought processes What is Artificial Intelligence The exciting new effort to make computers think.. Machines with minds, in the full and literal sense (Haugeland, 1985) Behavior The study of how to make computers do things at which, at the moment, people are better. (Rich, and Knight, 1991) Activities The automation of activities that we associate with human thinking, activities such as decision-making, problem solving, learning (Bellman)

AI as Raisin Bread Esther Dyson [predicted] AI would [be] embedded in main-stream, strategically important systems, like raisins in a loaf of raisin bread. Time has proven Dyson's prediction correct. Emphasis shifts away from replacing expensive human experts with stand-alone expert systems toward main-stream computing systems that create strategic advantage. Many of today's AI systems are connected to large data bases, they deal with legacy data, they talk to networks, they handle noise and data corruption with style and grace, they are implemented in popular languages, and they run on standard operating systems. Humans usually are important contributors to the total solution. Adapted from Patrick Winston, Former Director, MIT AI Laboratory

Agents and environments Compare: Standard Embedded System Structure sensors ADC microcontroller DAC actuators ASIC FPGA

The Turing Test (Can Machine think? A. M. Turing, 1950) Requires: Natural language Knowledge representation Automated reasoning Machine learning (vision, robotics) for full test

Acting/Thinking Humanly/Rationally Turing test (1950) Requires: Natural language Knowledge representation automated reasoning machine learning (vision, robotics.) for full test Methods for Thinking Humanly: Introspection, the general problem solver (Newell and Simon 1961) Cognitive sciences Thinking rationally: Logic Problems: how to represent and reason in a domain Acting rationally: Agents: Perceive and act

Agents An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators Human agent: eyes, ears, and other organs for sensors; hands, legs, mouth, and other body parts for actuators Robotic agent: cameras and infrared range finders for sensors; various motors for actuators

Agents and environments The agent function maps from percept histories to actions: [f: P* A] The agent program runs on the physical architecture to produce f agent = architecture + program

Vacuum-cleaner world Percepts: location and state of the environment, e.g., [A,Dirty], [B,Clean] Actions: Left, Right, Suck, NoOp

Rational agents Rational Agent: For each possible percept sequence, a rational agent should select an action that is expected to maximize its performance measure, based on the evidence provided by the percept sequence and whatever built-in knowledge the agent has. Performance measure: An objective criterion for success of an agent's behavior E.g., performance measure of a vacuum-cleaner agent could be amount of dirt cleaned up, amount of time taken, amount of electricity consumed, amount of noise generated, etc.

Rational agents Rationality is distinct from omniscience (all-knowing with infinite knowledge) Agents can perform actions in order to modify future percepts so as to obtain useful information (information gathering, exploration) An agent is autonomous if its behavior is determined by its own percepts & experience (with ability to learn and adapt) without depending solely on build-in knowledge

Discussion Items An realistic agent has finite amount of computation and memory available. Assume an agent is killed because it did not have enough computation resources to calculate some rare event that eventually that ended up killing it. Can this agent still be rational? The Turing test was contested by Searle by using the Chinese Room argument. The Chinese Room agent needs an exponential large memory to work. Can we save the Turing test from the Chinese Room argument?

Task Environment Before we design an intelligent agent, we must specify its task environment : PEAS: Performance measure Environment Actuators Sensors

PEAS Example: Agent = taxi driver Performance measure: Safe, fast, legal, comfortable trip, maximize profits Environment: Roads, other traffic, pedestrians, customers Actuators: Steering wheel, accelerator, brake, signal, horn Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard

PEAS Example: Agent = Medical diagnosis system Performance measure: Healthy patient, minimize costs, lawsuits Environment: Patient, hospital, staff Actuators: Screen display (questions, tests, diagnoses, treatments, referrals) Sensors: Keyboard (entry of symptoms, findings, patient's answers)

PEAS Example: Agent = Part-picking robot Performance measure: Percentage of parts in correct bins Environment: Conveyor belt with parts, bins Actuators: Jointed arm and hand Sensors: Camera, joint angle sensors

Environment types Fully observable (vs. partially observable): An agent's sensors give it access to the complete state of the environment at each point in time. Deterministic (vs. stochastic): The next state of the environment is completely determined by the current state and the action executed by the agent. (If the environment is deterministic except for the actions of other agents, then the environment is strategic) Episodic (vs. sequential): An agent s action is divided into atomic episodes. Decisions do not depend on previous decisions/actions.

Environment types Static (vs. dynamic): The environment is unchanged while an agent is deliberating. (The environment is semidynamic if the environment itself does not change with the passage of time but the agent's performance score does) Discrete (vs. continuous): A limited number of distinct, clearly defined percepts and actions. How do we represent or abstract or model the world? Single agent (vs. multi-agent): An agent operating by itself in an environment. Does the other agent interfere with my performance measure?

task environm. observable determ./ stochastic episodic/ sequential static/ dynamic discrete/ continuous agents crossword puzzle chess with clock fully determ. sequential static discrete single fully strategic sequential semi discrete multi poker back gammon taxi driving medical diagnosis image analysis partpicking robot refinery controller interact. Eng. tutor partial stochastic sequential dynamic continuous multi partial stochastic sequential dynamic continuous single fully determ. episodic semi continuous single partial stochastic episodic dynamic continuous single partial stochastic sequential dynamic continuous single partial stochastic sequential dynamic discrete multi

task environm. observable determ./ stochastic episodic/ sequential static/ dynamic discrete/ continuous agents crossword puzzle chess with clock fully determ. sequential static discrete single fully strategic sequential semi discrete multi poker partial stochastic sequential static discrete multi back gammon taxi driving medical diagnosis image analysis partpicking robot refinery controller interact. Eng. tutor partial stochastic sequential dynamic continuous multi partial stochastic sequential dynamic continuous single fully determ. episodic semi continuous single partial stochastic episodic dynamic continuous single partial stochastic sequential dynamic continuous single partial stochastic sequential dynamic discrete multi

task environm. observable determ./ stochastic episodic/ sequential static/ dynamic discrete/ continuous agents crossword puzzle chess with clock fully determ. sequential static discrete single fully strategic sequential semi discrete multi poker partial stochastic sequential static discrete multi back gammon taxi driving medical diagnosis image analysis partpicking robot refinery controller interact. Eng. tutor fully stochastic sequential static discrete multi partial stochastic sequential dynamic continuous multi partial stochastic sequential dynamic continuous single fully determ. episodic semi continuous single partial stochastic episodic dynamic continuous single partial stochastic sequential dynamic continuous single partial stochastic sequential dynamic discrete multi

Agent types Five basic types in order of increasing generality: Table Driven agents Simple reflex agents Model-based reflex agents Goal-based agents Utility-based agents

table lookup for entire history Table Driven Agent. current state of decision process

Simple reflex agents NO MEMORY Fails if environment is partially observable example: vacuum cleaner world

description of current world state Model-based reflex agents Model the state of the world by: modeling how the world changes how it s actions change the world This can work even with partial information It s is unclear what to do without a clear goal

Goal-based agents Goals provide reason to prefer one action over the other. We need to predict the future: we need to plan & search

Utility-based agents Some solutions to goal states are better than others. Which one is best is given by a utility function. Which combination of goals is preferred?

Learning agents How does an agent improve over time? By monitoring it s performance and suggesting better modeling, new action rules, etc. Evaluates current world state changes action rules suggests explorations old agent = model world and decide on actions to be taken