CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

24
CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

description

CSE 471/598 H. Liu3 All about Agents We will learn How agents should act Environments of agents Types of agents  human, robot, software agents A vacuum-cleaner world with 2 locations (Fig 2.2) Percepts: location and contents, e.g., [A,Dirty] Actions: Left, Right, Suck, NoOp A simple agent function(Fig 2.3) What is the right way to fill out the table? What makes an agent good or bad? We need to specify how agents should act in order to measure

Transcript of CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

Page 1: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598

Intelligent Agents TIP

We’re intelligent agents,aren’t we?

Page 2: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 2

IntroductionAn agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.We discuss A wide variety of agents How to define an agent

Let’s look at Figure 2.1 Is that me? An agent function maps percepts to

actions

Page 3: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 3

All about AgentsWe will learn

How agents should act Environments of agents Types of agents

human, robot, software agentsA vacuum-cleaner world with 2 locations (Fig 2.2)

Percepts: location and contents, e.g., [A,Dirty]

Actions: Left, Right, Suck, NoOp A simple agent function(Fig 2.3) What is the right way to fill out the

table?What makes an agent good or bad?

We need to specify how agents should act in order to measure

Page 4: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 4

How Agents should actA rational agent is one that does the right thing.

What is “right”? The issue of performance measure, is not a simple one You often get what you ask for. Be as objective as possible Measure what one wants, not how the agent should

behave E.g., how to be a rational instructor/student?

Do the right thing and be objective. How? Switch your positions (student, instructor, another

student) to increase objectivity A related issue is when to measure it.

How often to measure it

Page 5: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 5

A rational agent is not omniscient

Rationality is concerned with expected success given what has been perceivedA percept sequence contains everything that the agent has perceived so farAn ideal rational agent should do whatever action that maximize its expected performance Rationality does not mean perfection which

maximizes actual performance Do we sometimes regret? Do regrets help?

Why?

Page 6: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 6

Four key componentsWhat is rational depends on PEAS: Performance measure Environment Actuators – generating actions Sensors – receiving perceptsAnother example? Taxi driver (a robot in the future) Let’s think about its performance

measure Let’s now look at Fig 2.4

Page 7: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 7

Definition of a rational agentFor 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.

Page 8: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 8

From percept sequences to actions A mapping with possibly infinite entries An ideal mapping describes an ideal agent It’s not always necessary to have an explicit

mapping in order to be ideal (e.g., sqrt (x))An agent should have some autonomy. i.e., its behavior is determined by its own

experience. Autonomy can evolve with an agent’s

experience and percept sequence - learning.

Page 9: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 9

External environmentsWithout exception, actions are done by the agent on the environment, which in turn provides percepts to the agents.Environments affect the design of agents Types of environments

Page 10: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 10

Types of EnvironmentsFully vs. partially observableDeterministic vs. stochastic

E is deterministic but actions of other agents are not =>strategic

Episodic vs. sequential An example of episodic environment?

Static vs. dynamic E does not change, performance score does =>

semi-dynamicDiscrete vs. continuousSingle vs. multiple agentsWhat is the most difficult environment?

Let’s look at some examples in Fig 2.6

Are you impressed? What can we do

to improve?

Page 11: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 11

Design and Implementation of Agents

Design an agent function that maps the agent’s percepts to actions. Or to realize how actions are selected or

determinedImplement the agent function in an agent program which is realized in an agent architectureAgent = Architecture+ Program Percepts and actuators + function

mappingsFrom Robots to Softbots Architectures can be very different

Page 12: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 12

Some examples of agentsAll agents have four elements (PEAS):

1. Performance 2. Environment3. Actuators 4. Sensors

Fig 2.5 shows some agent types We can see that there are many ways

to define these components and it’s impractical to enumerate all possibilities

Page 13: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 13

Starting from the simplestA look-up agent (Fig 2.7) Generates actions based on percept sequences

Your decision today is determined by many things happened in the past

Why not just look up? How far back should we look up Scaling up An equivalent question is about the table size

What else should we try?

Page 14: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 14

Page 15: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 15

Types of agents Simple reflex agents - respond based on the current percept, ignore the percept history. It cuts down a lot of possibilities. An example (Fig 2.8) A simple reflex agent (Figs 2.9,2.10)

Condition-action Rules Innate reflexes vs. learned responses What if the environment is not fully

observable?

Page 16: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 16

Model-based reflex agentsThey can handle partial observability Knowledge about how the world works is called

a model of the worldMaintain internal state to keep information of the changing environment and involve consideration of the future Respond to a percept accordingly (Figs 2.12)

From local to global

Page 17: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 17

Page 18: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 18

Goal-based agents They aim to achieve goals Goal: desirable states, Search for a sequence of actions, Plan for solving sub-problems with

special purposesGoals alone are often not enough to generate high-quality behavior. Why?

Page 19: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 19

Page 20: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 20

Utility-based agentsThey aim to maximize their utilities Utility: the quality of being useful, a single

value function Happy or not (a goal or not) vs. How happy

when the goal is achieved resolve conflicting goals (speed vs. safety)evaluate with multiple uncertain qualities search for trade-off facing multiple goals

Page 21: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 21

Page 22: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 22

Learning agents They can learn to improve Operate in initially unknown environments

and become more competent Four components: (1) problem generator (to

create exploratory actions), (2) performance element (the earlier entire agent), (3) learner, (4) critic (to provide feedback)

The above types of agents can be found in the later chapters we will discuss.

Page 23: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 23

Page 24: CSE 471/598 Intelligent Agents TIP We’re intelligent agents, aren’t we?

CSE 471/598 H. Liu 24

SummaryThere are various types of agents who cannot live without external environment.Efficiency and flexibility of different agents.

Using ourselves as a model and our world as environment as a starting point (Are we too ambitious?), you mayDescribe options for future considerationRecommend a new type of agents (Novel Contribution!)