![Page 1: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/1.jpg)
ARTIFICIAL INTELLIGENCE
Intelligent Agents
April 21, 2023
1
![Page 2: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/2.jpg)
WHAT IS AN AGENT?
In general, an entity that interacts with its environmentperception through sensorsactions through effectors or actuators
April 21, 2023
2
![Page 3: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/3.jpg)
EXAMPLES OF AGENTS
Human agent eyes, ears, skin, taste buds, etc. for sensors hands, fingers, legs, mouth, etc. for actuators
powered by musclesRobot
camera, infrared, etc. for sensors wheels, lights, speakers, etc. for actuators
often powered by motorsSoftware agent
functions as sensorsinformation provided as input to functions in the form of encoded bit strings or symbols
functions as actuatorsresults deliver the output
April 21, 2023
3
![Page 4: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/4.jpg)
PERFORMANCE OF AGENTS
A rational agent does “the right thing”
Problems: what is “ the right thing” how do you measure the “best outcome”
Criteria for measuring the outcome and the expenses of the agent task dependent time may be important
April 21, 2023
4
![Page 5: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/5.jpg)
PERFORMANCE EVALUATION EXAMPLES
Vacuum agent number of tiles cleaned during a certain period
doesn’t consider expenses of the agent, side effectsenergy, noise, loss of useful objects, damaged furniture, scratched floor
might lead to unwanted activitiesagent re-cleans clean tiles, covers only part of the room, drops dirt on tiles to have more tiles to clean, etc.
April 21, 2023
5
![Page 6: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/6.jpg)
RATIONAL AGENT
Selects the action that is expected to maximize its performance based on a performance measure
successful completion of a task depends on the percept sequence, background
knowledge
April 21, 2023
6
![Page 7: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/7.jpg)
ENVIRONMENTS
Determine the interaction between the “outside world” and the agent the “outside world” is not necessarily the “real
world” as we perceive it
In many cases, environments are implemented within computers
April 21, 2023
7
![Page 8: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/8.jpg)
ENVIRONMENT PROPERTIES Fully observable vs. partially observable
sensors capture all relevant information from the environment
Deterministic vs. non-deterministic changes in the environment are predictable
Episodic vs. sequential (non-episodic) independent perceiving-acting episodes
Static vs. dynamic no changes while the agent is “thinking”
Discrete vs. continuous limited number of distinct percepts/actions
Single vs. multiple agents interaction and collaboration among agents competitive, cooperative
April 21, 2023
8
![Page 9: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/9.jpg)
FROM PERCEPTS TO ACTIONS
If an agent only reacts to its percepts, a table can describe the mapping from percept sequences to actions instead of a table, a simple function may also be
used can be conveniently used to describe simple
agents that solve well-defined problems in a well-defined environment e.g. calculation of mathematical functions
April 21, 2023
9
![Page 10: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/10.jpg)
VACBOT PAGE DESCRIPTION
Percepts
Actions
Goals
EnvironmentRoom and furniture
All tiles are clean
pick up dirt, move
tile properties like clean/dirty, empty/occupiedmovement and orientation
high-level characterization of agents
April 21, 2023
10
![Page 11: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/11.jpg)
LOOK IT UP!
Simple way to specify a mapping from percepts to actions tables may become very large all work done by the designer all actions are predetermined learning might take a very long time
April 21, 2023
11
![Page 12: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/12.jpg)
AGENT PROGRAM TYPES
Different ways of achieving the mapping from percepts to actions
Different levels of complexity
Simple reflex agents Agents that keep track of the world Goal-based agents Utility-based agents Learning agents
April 21, 2023
12
![Page 13: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/13.jpg)
SIMPLE REFLEX AGENT
Instead of specifying individual mappings in an explicit table, common input-output associations are recorded frequent method of specification is through condition-
action rules if percept then action
efficient implementation, but limited power environment must be fully observable
April 21, 2023
13
![Page 14: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/14.jpg)
REFLEX AGENT DIAGRAM
Sensors
Actuators
What the world is like now
What should I do now
Condition-action rules
Agent Environment
April 21, 2023
14
![Page 15: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/15.jpg)
REFLEX AGENT DIAGRAM 2
Sensors
Actuators
What the world is like now
What should I do now
Condition-action rules
Agent
Environment
April 21, 2023
15
![Page 16: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/16.jpg)
MODEL-BASED REFLEX AGENT
An internal state maintains important information from previous percepts sensors only provide a partial picture of the
environment helps with some partially observable
environments The internal states reflects the agent’s
knowledge about the world this knowledge is called a model may contain information about changes in the
world caused by actions of the action independent of the agent’s behavior
April 21, 2023
16
![Page 17: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/17.jpg)
MODEL-BASED REFLEX AGENT DIAGRAM
Sensors
Actuators
What the world is like now
What should I do now
State
How the world evolves
What my actions do
Agent
Environment
Condition-action rules
April 21, 2023
17
![Page 18: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/18.jpg)
GOAL-BASED AGENT
The agent tries to reach a desirable state, the goal may be provided from the outside (user, designer,
environment), or inherent to the agent itself Results of possible actions are considered with
respect to the goal Very flexible
April 21, 2023
18
![Page 19: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/19.jpg)
GOAL-BASED AGENT DIAGRAM
Sensors
Actuators
What the world is like now
What happens if I do an action
What should I do now
State
How the world evolves
What my actions do
Goals
Agent
Environment
April 21, 2023
19
![Page 20: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/20.jpg)
UTILITY-BASED AGENT
More sophisticated distinction between different world states a utility function maps states onto a real number
may be interpreted as “degree of happiness”
April 21, 2023
20
![Page 21: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/21.jpg)
UTILITY-BASED AGENT DIAGRAM
Sensors
Actuators
What the world is like now
What happens if I do an action
How happy will I be then
What should I do now
State
How the world evolves
What my actions do
Utility
Agent
Environment
April 21, 2023
21
![Page 22: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/22.jpg)
LEARNING AGENT
Performance element selects actions based on percepts, internal state,
background knowledge can be one of the previously described agents
Learning element identifies improvements
Critic provides feedback about the performance of the agent can be external; sometimes part of the environment
Problem generator suggests actions
April 21, 2023
22
![Page 23: A RTIFICIAL I NTELLIGENCE Intelligent Agents 30 November 2015 1](https://reader033.vdocuments.us/reader033/viewer/2022051001/56649f485503460f94c6a318/html5/thumbnails/23.jpg)
LEARNING AGENT DIAGRAM
Sensors
Actuators Agent
Environment
What the world is like now
What happens if I do an action
How happy will I be then
What should I do now
State
How the world evolves
What my actions do
Utility
Critic
Learning Element
ProblemGenerator
PerformanceStandard
April 21, 2023
23