1. Intelligent Agents
Marco Loog

2. Some Unnecessary Remark
Book is rather formal and strict, we probably won’t be [in a lot of cases]

3. From Chapter 1 What is AI? Two main considerations
Thinking <> behavior
Model humans <> ideal standard
Book is concerned with acting & ideals : acting rationally
[Good for games? Possible objections?]

4. More From Chapter 1 Acting rationally : rational agent
Agent : something that acts
Computer agent : operating under autonomous control, perceiving environment, adapting to change, capable of taking on another’s goal
Rational agent : acts so as to achieve the best [expected] outcome

5. And More... Book deals with
Intelligence that is concerned with rational action
General principles of rational agents and their construction
Ideally, intelligent agent takes best possible action
However, the issue of limited rationality is also discussed

6. Some More Unnecessary Remarks
We will regularly talk about AI without necessarily referring to games and / or exemplifying everything based on games
Academia <> practice
This may ask a lot from the student’s creativity, autonomy, imagination, etc.

7. Intelligent Agents We have determined what an intelligent agent is
In Chapter 2, agents, environments, and the interactions / relations between them are examined
Start out by a kind of taxonomy of possible agents and environments

8. Outline Agents and environments Rationality PEAS Environment types
Agent types

9. Agents and Environments
Agent : anything that can be viewed as
perceiving its environment through sensors
acting upon 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

10. Agents and Environments
Agent : anything that can be viewed as
perceiving its environment through sensors
acting upon environment through actuators
Percepts : agent’s perceptual inputs from the environment
Percept sequence : complete history of percepts
Generally, choice of action can depend on entire percept sequence

11. Agents and Environments
If possible to specify agent’s action for every percept sequence, then agent is fully defined
Agent’s complete behavior is described by this specification, which is called the agent function

12. Agents and Environments
If possible to specify agent’s action for every percept sequence, then agent is fully defined
Agent’s complete behavior is described by this specification, which is called the agent function
Mathematically, the agent function f maps percept histories P to actions A; f:P -> A
Note that P’s cardinality is often infinite and therefore tabulating it is impossible

13. Agents and Environments
Agent function is actually implemented via an agent program, which runs on the agent architecture
Agent program runs on the physical architecture to produce f
Agent := agent function + agent architecture

14. Schematically...

15. Vacuum-Cleaner World Percepts : location and contents, e.g., [A,Dirty]
Actions: Left, Right, Suck, NoOp [do nothing]

16. A Vacuum-Cleaner Agent

17. ?
What is the right way to fill out the previous percept sequence / action table?
What makes an agent good? What makes it bad?
How about intelligent?

18. Rational Agents Agent should strive to “do the right thing” using
What it can perceive
The actions it can perform
Right action : one that will cause the agent to be most successful
Performance measure : objective criterion for measuring agent’s success

19. “General Rule”
It is better to design performance measures according to what one actually wants in the environment, rather than according to how one thinks the agent should behave
True?
And for games? [FSM?]
One way or the other : this might be very difficult

20. For Our Vacuum-Cleaner Agent
Possible performance measures
Amount of dirt cleaned up?
Amount of time taken?
Amount of electricity consumed?
Amount of noise generated?
Etc.?

21. At the Risk of Somehow Repeating Myself Too Often...
What is rational for an agent depends on the following
Performance measure that defines success
Prior knowledge of the environment
Possible actions
Percept sequence to date

22. Definition of 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, a priori knowledge the agent has

23. Some Necessary Remarks
Rationality is distinct from omniscience
Agents can perform actions to modify future percepts to obtain useful information [gathering / exploration]
An agent is autonomous if its behavior is determined by its own experience [with the ability to learn and adapt]
Initial agent configuration could reflect prior knowledge, but may be modified and augmented based on its experience
Let game agent adapt to new environment...

24. More : Agent Function
Successful agents split up the task of determining the agent function in three periods
Design : certain perception / action relations are directly available; f is partially pre-defined
‘In action’, while functioning : need for additional calculations before deciding on an action; right way to apply f
Learning from experience : mapping between percept sequence an actions is reconsidered; f is altered

25. And More : Autonomy
The more agent relies on prior knowledge of its designers, and the less on its percepts, the less autonomous it is
“A rational agent should be autonomous—it should learn what it can to compensate for partial or incorrect prior knowledge”
Do we agree?

26. Autonomy in Practice[?]
In practice, an agent may start with some prior knowledge + ability to learn
“Hence, the incorporation of learning allows one to design a single rational agent that will succeed in a vast variety of environments”

27. Task Environments
Before actually building rational agents, we should consider their environment
Task environment : the ‘problems’ to which rational agents are the ‘solutions’

28. Task Environment & PEAS
PEAS : Performance measure, Environment, Actuators, Sensors
Must first specify these setting for intelligent agent design

29. PEAS Consider 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

30. Mo’ PEAS 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]

31. Mo’ PEAS 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 Fully observable [vs. partially observable]
Agent's sensors give access to complete state of the environment at each point in time
Fully observable leads to cheating...
Deterministic [vs. stochastic]
Next state of the environment is completely determined by the current state and the action executed by the agent.
Strategic : deterministic except actions of other agents
Episodic [vs. sequential]
Agent's experience is divided into atomic ‘episodes’ [perceiving and performing a single action]; choice of action in each episode depends only on the episode itself

33. Deterministic [vs. Stochastic]
In reality, situations are often so complex that they may are better treated as stochastic [even if they are deterministic]
[Luckily, we all like probability theory, statictics, etc., i.e., the appropriate tools for describing these environments]

34. Environment Types Static [vs. dynamic] Discrete [vs. continuous]
Environment is unchanged while an agent is deliberating
Semidynamic : environment itself not change over time but agent’s performance score does
Anyone playing chess? Clock -> semidynamic?
Discrete [vs. continuous]
Limited number of distinct, clearly defined percepts and actions
Not clear-cut in practice
Single agent [vs. multi-agent]
Agent operating by itself in an environment

35. Single [vs. Multi-Agent]
Some subtle issue
Which entities must be viewed as agents? The ones maximizing a performance measure, which depends on other agents
Competitive [vs. cooperative] environment
Pursuing goal of maximizing performance measure implies minimizing some other agent’s measure, e.g. as in chess

36. Environment Types [E.g]
Chess with Chess without Taxi a clock a clock driving
Fully observable Yes Yes No
Deterministic Strategic Strategic No
Episodic No No No
Static Semi Yes No
Discrete Yes Yes No
Single agent No No No
Environment type largely determines agent design
Real world is [of course] partially observable, stochastic, sequential, dynamic, continuous, multi-agent
Not always cut and dried / definition dependent
Chess again... : castling? En passant capture? Draws by repetition?

37. How About the Inside?
Earlier : mainly only gave description of agent’s behavior, i.e., action that is performed following any percept sequence, i.e., the agent function
Agent = architecture + program
Job of AI : design agent program that implements agent function
Architectures is, more or less, assumed to be given; in games [and other applications] design may take place simultaneously

38. 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 [= optimal]
Aim : find a way to implement the rational agent function concisely

39. Table-lookup Agent
Lookup table that relates every percept sequence to the appropriate action
Drawbacks
Huge table [really huge in many cases]
Take a long time to build the table [virtually infinite in many cases] No autonomy
Even with learning, need a long time to learn the table entries
However, it does what it should do...

40. Key Challenge for AI
Find out how to write programs that, to the extent possible, produce rational behavior from a small amount of code [‘rules’] rather than from a large number of table entries

41. Four Basic Agent Types
Four basic types of agent programs embodying principles of almost every intelligent system
In order of increasing generality
Simple reflex
Model-based reflex
Goal-based
Utility-based

42. Simple Reflex
Agent selects action on the basis of current percept [if... then...]

43. Program for a Vacuum-Cleaner

44. From Simple Reflex to...
Simple reflex agents work only if the environment is fully observable, because decision should be made on the current percept

45. Model-Based Reflex
Effective way to handle partial observability is keeping track of every part of the environment the agent cannot see now
Some internal state should be maintained, which is based on the percept sequence, and which reflects some of the unobserved aspects of the current state

46. Internal State
Updating requires the encoding of two types of knowledge in the program
Knowledge about evolution of the world independent of the agent
How do own actions influence the environment?
Knowledge about world = model of world
Model-based agent

47. Model-Based Reflex

48. From Model-Based Reflex to...
Knowledge about current state of the world not always enough
In addition, it may be necessary to define a goal / situation that is desirable

49. Goal-Based

50. From Goal-Based to...
For most environments, goals alone are not really enough to generate high-quality behavior
There are many ways in which one achieve a goal...
Instead, measure utility [‘hapiness’]
Utility function maps states onto real numbers describing degree of hapiness
Can perform tradeoff if there are several ways to a goal, or if there are multiple goals [using likelihood]

51. Utility-Based

52. Two Remarks on Utility
Rather theoretical result : any rational agent must behave as if it possesses a utility function whose expected value it tries to maximize
Utility-based agent programs are used let an agent handle inherent uncertainty in partially observable worlds

53. But How... ...do these agent programs come into existence?
The particular method suggested by Turing [the one from that machine] is to build learning agents, that should subsequently be teached
One of the advantages of these agents is that they can [learn to] deal with unknown environments

54. Learning Agent Four conceptual components
Learning element : responsible for making improvements
Performance element : responsible for external actions [previously considered equal to entire agent]
Critic : provides feedback on how agent is doing and determines how performance element should be modified
Problem generator : responsible for suggesting actions leading to new and informative experience

55. Learning Agent

56. Next Week
More...