Scribd
Upload
353 views13 pages

PEAS Description of Task Environment With Different Types of Properties

This document describes PEAS (Performance, Environment, Actuators, Sensors) and properties of task environments. PEAS defines the key components of an agent's task environment, including the performance measure, surrounding environment, means of output/input. An example is given of PEAS for a self-driving car. Properties of task environments that are discussed include whether they are fully/partially observable, deterministic/stochastic, episodic/sequential, single/multi-agent, static/dynamic, and discrete/continuous.

Uploaded by

Monir Ahammod
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
353 views13 pages

PEAS Description of Task Environment With Different Types of Properties

This document describes PEAS (Performance, Environment, Actuators, Sensors) and properties of task environments. PEAS defines the key components of an agent's task environment, including the performance measure, surrounding environment, means of output/input. An example is given of PEAS for a self-driving car. Properties of task environments that are discussed include whether they are fully/partially observable, deterministic/stochastic, episodic/sequential, single/multi-agent, static/dynamic, and discrete/continuous.

Uploaded by

Monir Ahammod
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

PEAS description of task environment

with different types of properties


Presented by Supervised by
Md. Monir Ahammod Md. Nesarul Hoque
16CSE061 Assistant Professor,
Department of Computer Department of Computer
Science and Engineering Science and Engineering
BSMRSTU BSMRSTU
Contents
What is PEAS ?
PEAS Description.
Example of PEAS.
Properties of task environments.

1
What is PEAS ?
 PEAS is under the heading of the task environment.
 When we define a rational agent, we group these properties under
PEAS, the problem specification for the task environment.
 PEAS stands for:
– Performance
– Environment
– Actuators
– Sensors

2
PEAS Description
 Performance Measure: Performance measure is the unit to define the
success of an agent.
 Environment: Environment is the surrounding of an agent at every
instant.
 Actuator: Actuator is a part of the agent that delivers the output of an
action to the environment.
 Sensor: Sensors are the receptive parts of an agent which takes in the
input for the agent.

3
Example of PEAS.
 What is PEAS for a self-driving car?

•Performance: Safety, time, legal drive, comfort.


•Environment: Roads, other cars, pedestrians, road signs.
•Actuators: Steering, accelerator, brake, signal, horn.
•Sensors: Camera, sonar, GPS, Speedometer, odometer, accelerometer,
engine sensors, keyboard
4
Properties of task environments/Environment types/task
environments behavior.

 Fully Observable vs Partially Observable


 Deterministic vs Stochastic
 Episodic vs sequential
 Single-agent vs Multi-agent
 Static vs Dynamic
 Discrete vs Continuous

5
Fully Observable vs Partially Observable
 When an agent sensor is capable to sense or access the complete state
of an agent at each point in time, it is fully observable environment
else partially observable.
 Example:
Chess – the board is fully observable, so are the opponent’s moves.
Driving – the environment is partially observable because what’s
around the corner is not known.

6
Deterministic vs Stochastic
 When the agent’s current state completely determines the next state of
the agent, the environment is deterministic.
 The stochastic environment is random in nature which is not unique
and cannot be completely determined by the agent.
 Example: 
Chess – there would be only a few possible moves for a coin at the
current state and these moves can be determined. 
Self Driving Cars – the actions of a self-driving car are not unique, it
varies time to time.

7
Episodic vs sequential
 In each the next episode does not depend on the actions taken in
previous episodes.
 In sequential environments, on the other hand, the current decision
could affect all future decisions.
 Part picking robot is episode.
 Chess and taxi driving are sequential.

8
Single-agent vs Multi-agent
 An environment consisting of only one agent is said to be a single-
agent environment.
 A person left alone in a maze is an example of the single-agent system.
 An environment involving more than one agent is a multi-agent
environment.
 The game of football is multi-agent as it involves 11 players in each
team is an example of the multi-agent system.

9
Static vs Dynamic
 Static environment changing itself when the agent is up with some
action is said to be dynamic.
 A roller coaster ride is dynamic as it is set in motion and the
environment keeps changing every instant.
 An idle environment with no change in its state is static environment.
 An empty house is static as there’s no change in the surroundings
when an agent enters.

10
Discrete vs Continuous
 If an environment consists of a finite number of actions, it is said to be
a discrete environment.
 The game of chess is discrete as it has only a finite number of moves.
 The environment in which the actions performed cannot be numbered
i.e. is not discrete, is said to be continuous.
 Self-driving cars are an example of continuous environments.

11
Thanks All

12

You might also like