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

2. 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 华刚

3. Course Information (1)  CS541 Artificial Intelligence  Term: Fall 2013  Instructor: Prof. Gang Hua  Class time: Tuesday 2:00pm—4:30pm  Location: EAS 330  Office Hour: Wednesday 4:00pm—5:00pm by appointment  Office: Lieb/Room305  Course Assistant: Yizhou Lin  Course Website:  http://www.cs.stevens.edu/~ghua/ghweb/ teaching/CS541Fall2013.htm

4. Course Information (2)  Text Book:  Stuart Russell and Peter Norvig, “Artificial Intelligence: A Modern Approach”, Third Edition, Prentice Hall, December 11, 2009 (Required)  Grading:  Class Participation: 10%  5 Homework: 50% (including a midterm project)  Final Project & Presentation: 40%

5. Schedule WeekDateTopicReadingHomework** 108/27/2013Introduction & Intelligent AgentCh 1 & 2N/A 209/03/2013Search: search strategy and heuristic searchCh 3 & 4sHW1 (Search) 309/10/2013Search: Constraint Satisfaction & Adversarial SearchCh 4s & 5 & 6 Teaming Due 409/17/2013Logic: Logic Agent & First Order LogicCh 7 & 8sHW1 due, Midterm Project (Game) 509/24/2013Logic: Inference on First Order LogicCh 8s & 9 610/01/2013Uncertainty and Bayesian Network Ch 13 & Ch14s HW2 (Logic) 7 10/08/2013Midterm Presentation Midterm Project Due 8 10/15/2013No class 9 10/22/2013Inference in Baysian NetworkCh 14sHW2 Due, HW3 (Probabilistic Reasoning) 10 10/29/2013Probabilistic Reasoning over TimeCh 15 11 11/05/2013Machine LearningCh 18 & 20 HW3 due, 1211/12/2013Markov Decision Process Ch 16 HW4 (Probabilistic Reasoning Over Time) 1311/19/2013Reinforcement learningCh 21HW4 due 1411/26/2013No class Q/A for final project 15 12/03/2013No class TA assisted Dry run 1612/10/2013Final Project Competition Final Project Due

6. Rules  Need to be absent from class?  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 ghua@stevens.edu

8. Introduction to Artificial Intelligence Chapter 1

9. What is AI? Systems thinking humanlySystems thinking rationally Systems acting humanlySystems 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  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  1943 McCulloch & Pitts: Boolean circuit model of brain  1950 Turing's "Computing Machinery and Intelligence"  1956Dartmouth meeting: "Artificial Intelligence" adopted  1952—69Look, Ma, no hands!  1950sEarly AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine  1965Robinson's complete algorithm for logical reasoning  1966—74AI discovers computational complexity Neural network research almost disappears  1969—79Early 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  2010-- BIG data? Deep learning?

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)  DeepBlue DeepBlue  Watson (DeepQA) 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?

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:  Performance measure?? 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:  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

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) SolitaireBackgammonInternet ShoppingTaxi Observable?Yes No Deterministic?YesNoPartlyNo Episodic?No Static?YesSemi No Discrete?Yes No Single Agent?YesNoYes (except auction)No  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  One agent function (or a small equivalence class) is rational 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 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:  Mastermind (midterm)  http://en.wikipedia.org/wiki/Mastermind_%28board_game%29 http://en.wikipedia.org/wiki/Mastermind_%28board_game%29  Final Projects:  Reversi (Othello)  http://en.wikipedia.org/wiki/Reversi http://en.wikipedia.org/wiki/Reversi