1. CS541 Artificial Intelligence
Lecture I: Introduction and Intelligent Agent

2. 华刚 Self-introduction Prof. Gang Hua
Associate Professor in Computer Science
Stevens Institute of Technology
Research Staff Member (07/2010—08/2011)
IBM T J. Watson Research Center
Senior Researcher (08/2009—07/2010)
Nokia Research Center Hollywood
Scientist (07/2006—08/2009)
Microsoft Live Labs Research
Ph.D. in ECE, Northwestern University, 06/2006

3. Course Information (1) CS541 Artificial Intelligence Term: Fall 2012
Instructor: Prof. Gang Hua
Class time: Wednesday 6:15pm—8:40pm
Location: Babbio Center/Room 210
Office Hour: Wednesday 4:00pm—5:00pm by appointment
Office: Lieb/Room305
Course Assistant: Yizhou Lin
Course Website:
cs541_artificial_intelligence_fall_2012.htm

4. Course Information (2) Text Book: Grading:
Stuart Russell and Peter Norvig, “Artificial Intelligence: A Modern Approach”, Third Edition, Prentice Hall, December 11, (Required)
Grading:
Class Participation: 10%
5 Homework: 50% (including a midterm project)
Final Project & Presentation: 40%

5. Schedule Week Date Topic Reading Homework** 1 08/29/2012
Introduction & Intelligent Agent
Ch 1 & 2
N/A 2
09/05/2012
Search: search strategy and heuristic search
Ch 3 & 4s
HW1 (Search) 3
09/12/2012
Search: Constraint Satisfaction & Adversarial Search
Ch 4s & 5 & 6
 Teaming Due 4
09/19/2012
Logic: Logic Agent & First Order Logic
Ch 7 & 8s
HW1 due, Midterm Project  (Game) 5
09/26/2012
Logic: Inference on First Order Logic
Ch 8s & 9 6
10/03/2012
No class  7
10/10/2012
Uncertainty and Bayesian Network
 Ch 13 & Ch14s
 HW2 (Logic) 8
10/17/2012
Midterm Presentation
Midterm Project Due 9
10/24/2012
Inference in Baysian Network
Ch 14s
HW2 Due, HW3 (Probabilistic Reasoning) 10
10/31/2012
Probabilistic Reasoning over Time
Ch 15 11
11/07/2012
Machine Learning
 HW3 due, 12
11/14/2012
Markov Decision Process
Ch 18 & 20
HW4 (Probabilistic Reasoning Over Time)
 13
11/21/2012
Ch 16 14
11/29/2012
Reinforcement learning
Ch 21
HW4 due 15
12/05/2012
Final Project Presentation
Final Project Due

6. Rules Need to be absent from class? Late submission of homework?
1 point per class: please send notification and justification at least 2 days before the class
Late submission of homework?
The maximum grade you can get from your late homework decreases 50% per day
Zero tolerance on plagiarism!!
You receive zero grade

7. Introduction & Intelligent Agent
Prof. Gang Hua
Department of Computer Science
Stevens Institute of Technology

8. Introduction to Artificial Intelligence
Chapter 1

9. Systems thinking humanly Systems thinking rationally
What is AI?
Systems thinking humanly
Systems thinking rationally
Systems acting humanly
Systems acting rationally

10. Acting humanly: Turing Test
Turing (1950) "Computing machinery and intelligence":
"Can machines think?"  "Can machines behave intelligently?"
Operational test for intelligent behavior: the Imitation Game
Predicted that by 2000, a machine might have a 30% chance of fooling a layperson for 5 minutes
Anticipated all major arguments against AI in following 50 years
Suggested major components of AI: knowledge, reasoning, language understanding, learning,
Total Turing test: adding vision and robotics
Problem: Turing test is not reproducible, constructive, or amenable to mathematical analysis

11. Thinking humanly: cognitive modeling
1960 "cognitive revolution": information-processing psychology replaced prevailing orthodoxy of behaviorism
Requires scientific theories of internal activities of the brain
What levels of abstraction? "Knowledge" or "circuits"?
How to validate? Requires
Predicting and testing behavior of human subjects (top-down)
Direct identification from neurological data (bottom-up)
Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now distinct from AI
Both share one principal direction with AI:
The available theories do not explain anything resembling human-level general intelligence

12. Thinking rationally: "laws of thought"
Aristotle: what are correct arguments/thought processes?
Several Greek schools developed various forms of logic:
notation and rules of derivation for thoughts;
They may or may not have proceeded to the idea of mechanization
Direct line through mathematics and philosophy to modern AI
Problems:
Not all intelligent behavior is mediated by logical deliberation
What is the purpose of thinking?
What thoughts should I have out of all the thoughts (logical or otherwise) that I could have?

13. Acting rationally: rational agent
Rational behavior: doing the right thing
The right thing: that which is expected to maximize goal achievement, given the available information
Doesn't necessarily involve thinking – e.g., blinking reflex – but thinking should be in the service of rational action
Aristotle (Nicomachean Ethics):
Every art and every inquiry, and similarly every action and pursuit, is thought to aim at some good

14. Rational agents An agent is an entity that perceives and acts
This course is about designing rational agents
Abstractly, an agent is a function from percept histories to actions:
For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance
Caveat: computational limitations make perfect rationality unachievable
 design best program for given machine resources

15. AI prehistory Philosophy Mathematics Economics Neuroscience Psychology
Logic, methods of reasoning, mind as physical system, foundations of learning, language, rationality
Mathematics
Formal representation and proof algorithms, computation, (un)decidability, (in)tractability, probability
Economics
Utility, decision theory
Neuroscience
Physical substrate for mental activity
Psychology
Phenomena of perception and motor control, experimental techniques
Computer engineering
Building fast computers
Control theory
Design systems that maximize an objective function over time
Linguistics
knowledge representation, grammar

16. Abridged history of AI
McCulloch & Pitts: Boolean circuit model of brain
Turing's "Computing Machinery and Intelligence"
1956 Dartmouth meeting: "Artificial Intelligence" adopted
1952—69 Look, Ma, no hands!
1950s Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine
1965 Robinson's complete algorithm for logical reasoning
1966—74 AI discovers computational complexity Neural network research almost disappears
1969—79 Early development of knowledge-based systems
1980—88 Expert systems industry boom
1988—93 Expert systems industry busts: "AI Winter"
1985—95 Neural networks return to popularity
1988— Resurgence of probability; AI becomes science
1995— The emergence of intelligent agents
2003— Human-level AI back on the agenda

17. State of the art
Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997
Proved a mathematical conjecture (Robbins conjecture) unsolved for decades
No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego)
During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people
NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft
Proverb solves crossword puzzles better than most humans
iRobot corporated in 2000: Roomba & Scooba
Google cars automatically are driving in the city to collect stree-tview images
Watson whips Brad Rutter and Ken Jennings in Jeopardy in 2011!

18. DeepBlue & Watson (DeepQA)

19. Intelligent Agent
Chapter 2

20. Outline Agents and environments Rationality: what is a rational agent?
PEAS (Performance measure, Environment, Actuators, Sensors)
Environment types
Agent types

21. 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

22. Agents and environments
The agent function maps from percept histories to actions:
The agent program runs on the physical architecture to produce f
agent = architecture + program

23. Vacuum-cleaner world Percepts: location and contents, e.g., [A,Dirty]
Actions: Left, Right, Suck, NoOp

24. Rational agents (1)
An agent should strive to "do the right thing", based on what it can perceive and the actions it can perform. The right action is the one that will cause the agent to be most successful
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 in time T?
Amount of dirt cleaned up minus the amount of electricity consumed in time T?
Amount of time taken to clean a fixed region?
amount of dirt cleaned up, amount of time taken, amount of electricity consumed, amount of noise generated, etc.

25. Rational agents (2)
Rational Agent: For each possible percept sequence, a rational agent should select an action that is expected to maximize its performance measure, given the evidence provided by the percept sequence and whatever built-in knowledge the agent has.

26. Rational agents (3)
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 experience (with ability to learn and adapt)

27. PEAS (1) PEAS: Performance measure, Environment, Actuators, Sensors
To design a rational agent, we must first specify the task environment
Consider, e.g., the task of designing an automated taxi driver:
Environment??
Actuators??
Sensors??

28. PEAS (2)
To design a rational agent, we must first specify the task environment
Consider, e.g., the task of designing an automated taxi driver:
Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard

29. PEAS (3) Agent: Internet shopping agent
Performance measure: price, quality, appropriateness, efficiency
Environment: current and future WWW sites, vendors, shippers
Actuators: display to user, follow URL, fill in form
Sensors: HTML pages (text, graphics, scripts)

30. PEAS (4) 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

31. PEAS (5) Agent: Interactive English tutor
Performance measure: Maximize student's score on test
Environment: Set of students
Actuators: Screen display (exercises, suggestions, corrections)
Sensors: Keyboard

32. Environment types (1)
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): The agent's experience is divided into atomic "episodes" (each episode consists of the agent perceiving and then performing a single action), and the choice of action in each episode depends only on the episode itself.

33. Environment types (2)
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.
Single agent (vs. multiagent): An agent operating by itself in an environment.

34. Environment types (3)
Solitaire
Backgammon
Internet Shopping
Taxi
Observable?
Yes No
Deterministic?
Partly
Episodic?
Static?
Semi
Discrete?
Single Agent?
Yes (except auction)
The environment type largely determines the agent design
The real world is (of course) partially observable, stochastic, sequential, dynamic, continuous, multi-agent

35. Agent functions and programs
An agent is completely specified by the agent function mapping percept sequences to actions
Aim: find a way to implement the rational agent function concisely

36. Table-lookup agent Drawbacks: Huge table
Take a long time to build the table
No autonomy
Even with learning, need a long time to learn the table

37. A vacuum-cleaner agent
What is the right function?
Can it be implemented in a small agent program?

38. Agent types Four basic types (with increasing generality):
Simple reflex agents
Model-based reflex agents
Goal-based agents
Utility-based agents
All of them can be transformed into learning agent

39. Simple reflex agents
The action to be selected only depends on the most recent percept, not a sequence
These agents are stateless devices which do not have memory of past world states

40. Model-based reflex agents
Have internal state which is used to keep track of past states of the world
Can assist an agent deal with some of the unobserved aspects of the current state

41. Goal-based agents
Agent can act differently depending on what the final state should look like
E.g., automated taxi driver will act differently depending on where the passenger wants to go

42. Utility-based agents
An agent's utility function is an internalization of the external performance measure
They may differ if the environment is not completely observable or deterministic

43. Learning agents
Learning agent cuts across all of the other types of agents: any kind of agent can learn

44. iRobot
Roomba Demo

45. Summary
Agents interact with environments through actuators and sensors
The agent function describes what the agent does in all circumstances
The performance measure evaluates the environment sequence
A perfectly rational agent maximizes expected performance
Agent programs implement (some) agent functions
PEAS descriptions define task environments
Environments are categorized along several dimensions:
Observable? Deterministic? Episodic? Static? Discrete? Single-agent?
Several basic agent architectures exist:
Reflex, Reflex with state, goal-based, utility-based

46. Candidate projects Midterm Project: Final Projects:
Mastermind (midterm)
Final Projects:
Reversi (Othello)