CSE 573 Artificial Intelligence Dan Weld Peng Dai .

15
CSE 573 Artificial Intelligence Dan Weld Peng Dai www.cs.washington.edu/education/courses/ cse573/08au

Transcript of CSE 573 Artificial Intelligence Dan Weld Peng Dai .

Page 1: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

CSE 573 Artificial Intelligence

Dan WeldPeng Dai

www.cs.washington.edu/education/courses/cse573/08au

Page 2: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld 2

Logistics:• Reading for next class

  Finish R&N chapter 3  Start chapter 4 (thru 4.2)

• How do you find the book?

Page 3: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld 3

Topics• Intro: overview, agents

• Search: problem spaces, heuristic generation, CSPs

• Knowledge representation: prop & 1st logic

• Planning: time, regression, SAT compile, …

• Learning: dec trees, overfitting, bias, ensembles, semi supervision

• Uncertainty: stat learning, HMMs, DBNs, Markov networks, EM

• Natural language: information extraction

• Planning under uncertainty: MDPS, reinforcement learning

• Special topics

Page 4: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld 4

What is an ‘Agent’?

Page 5: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Intelligent Agents• Have sensors, effectors• Implement mapping from percept

sequence to actions

• Performance measure

Environment Agent

percepts

actions

Page 6: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Agent Function vs. Program• What is an ‘agent function’?

“If we can specify the agent’s choice of action for every possible percept sequence, then we have said more or less everything there is to say about the agent.” – R&N

Environment Agent

percepts

actions

Page 7: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld 7

Are Toasters Agents?

Page 8: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Defn: Ideal rational agent

• Rationality vs omniscience?• Acting in order to obtain valuable information

“For each possible percept sequence, does

whatever action is expected to maximize its

performance measure on the basis of evidence

perceived so far and built-in knowledge.''

Page 9: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Defn: Autonomy

An agent is autonomous to the extent that its behavior is determined by its own experience

Why is this important?

The parable of the dung beetle

Page 10: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Implementing ideal rational agent

• Table lookup agents• Agent program

  Simple reflex agents  Agents with memory

•Reflex agent with internal state•Goal-based agents•Utility-based agents

Page 11: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Simple reflex agentsE

NV

IRO

NM

EN

T

AGENT

Effectors

Sensors

what world islike now

Condition/Action ruleswhat action should I do now?

Page 12: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Reflex agent with internal state

EN

VIR

ON

ME

NT

AGENT Effectors

Sensors

what world islike now

Condition/Action ruleswhat action should I do now?

What world was like

How world evolves

Page 13: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Goal-based agentsE

NV

IRO

NM

EN

T

AGENT Effectors

Sensors

what world islike now

Goalswhat action should I do now?

What world was like

How world evolves

what it’ll be likeif I do acts A1-An

What my actions do

Page 14: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Utility-based agentsE

NV

IRO

NM

EN

T

AGENT Effectors

Sensors

what world islike now

Utility functionwhat action should I do now?

What world was like

How world evolves

What my actions do

How happy would I be?

what it’ll be likeif I do acts A1-An

Page 15: CSE 573 Artificial Intelligence Dan Weld Peng Dai .

© Daniel S. Weld

Properties of Environments

• Observability: full vs. partial vs. non

• Deterministic vs. stochastic• Episodic vs. sequential• Static vs. … vs. dynamic• Discrete vs. continuous

• Travel agent

• WWW shopping agent

• Coffee delivery mobile robot