Scribd
Upload
234 views

Artificial Intelligence: Agents and Environment

The document discusses different types of environments that agents can operate in, including: fully vs partially observable; deterministic vs stochastic; static vs dynamic; discrete vs continuous; and single agent vs multi-agent. It also describes different types of agent architectures, such as table-based agents, percept-based agents, state-based agents, goal-based agents, and utility-based agents. Finally, it discusses the importance of learning agents for operating autonomously in unknown environments.

Uploaded by

Hashim Omar Abukar
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
234 views

Artificial Intelligence: Agents and Environment

The document discusses different types of environments that agents can operate in, including: fully vs partially observable; deterministic vs stochastic; static vs dynamic; discrete vs continuous; and single agent vs multi-agent. It also describes different types of agent architectures, such as table-based agents, percept-based agents, state-based agents, goal-based agents, and utility-based agents. Finally, it discusses the importance of learning agents for operating autonomously in unknown environments.

Uploaded by

Hashim Omar Abukar
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 27

Agents and Environment

Artificial Intelligence

CHAPTER 4
Introduction to

Artificial Intelligence
COURSE OBJECTIVES

Discuss the agent environment

Discuss different types of environment

Explain different agent architectures


Introduction to

Artificial Intelligence
AGENT ENVIRONMENT

Every agent has specific environment


suited to work in.
If the agents environment is changed, it
effects the agent and makes the agent
not useful.
Introduction to

Artificial Intelligence
AGENT ENVIRONMENT

Environments in which agents operate


can be defined in different ways.
Its helpful to view the following definitions
as referring to the way the environment
appears from the point of view of the
agent itself.
Introduction to

Artificial Intelligence
ENVIRONMENT: OBSERVABILITY

Fully observable
 All of the environment relevant to the action being
considered is observable
 Such environments are convenient, since the agent
is freed from the task of keeping track of the
changes in the environment.
 Example:
• Full observable: Chess
Introduction to

Artificial Intelligence
ENVIRONMENT: OBSERVABILITY

Partially observable
 The relevant features of the environment are only
partially observable
 Example:
• Partially observable: Poker
Introduction to

Artificial Intelligence
ENVIRONMENT: DETERMINISM

Deterministic: The next state of the environment is


completely described by the current state and the
agent’s action. Image analysis
Introduction to

Artificial Intelligence
Environment: Determinism

Stochastic: if an element of interference or uncertainty


occurs then the environment is stochastic. Note that a
deterministic yet partially observable environment will
appear to be stochastic to the agent. Ludo
Introduction to

Artificial Intelligence
Environment: Determinism

Strategic: environment state wholly determined by the


preceding state and the actions of multiple agents is
called strategic. Chess
Introduction to

Artificial Intelligence
Environment: Episodicity

Episodic/sequential
An episodic environment means that
subsequent episodes do not depend on what
actions occurred in previous episodes
Introduction to

Artificial Intelligence
Environment: Episodicity

Episodic/sequential
In a sequential environment, the agent
engages in a series of connected episodes.
Introduction to

Artificial Intelligence
Environment: Dynamism

Static Environment: does not change from one state


to the next while the agent is considering its course of
action. The only changes to the environment as those
caused by the agent itself
Introduction to

Artificial Intelligence
Environment: Dynamism

Dynamic Environment: changes over time


independent of the actions of the agent – and thus if an
agent does not respond in a timely manner, this counts
as a choice to do nothing.
 Interactive tutor
Introduction to

Artificial Intelligence
Environment: Dynamism

Static/Dynamic
A static environment does not change while
the agent is thinking.
The passage of time as an agent deliberates
is irrelevant.
The agent doesn’t need to observe the world
during deliberation.
Introduction to

Artificial Intelligence
Environments: Continuity

Discrete/Continuous
If the number of distinct percepts and actions
is limited, the environment is discrete,
otherwise it is continuous
Introduction to

Artificial Intelligence
Environment: other agents

Single agent/Multi agent


If the environment contains other intelligent
agents, the agent needs to be concerned
about strategic, game-theories aspects of the
environment (for either cooperative or
competitive agents)
Introduction to

Artificial Intelligence
Complex Environments
Complexity of the environments include
Knowledge rich: enormous amount of
information that the environment contains
and
Input rich: the enormous amount of input
the environment can send to an agent.
Introduction to

Artificial Intelligence
Complex Environments
The agent must have a way of managing
this complexity. Often such
considerations lead to the development of
Sensing strategies and
Attentional mechanisms
So that the agent may more readily focus
its efforts in such rich environments
Introduction to

Artificial Intelligence
Table based agents
Information comes from sensors –
percepts
Look it up!
Triggers actions through the effectors

No notion of history, the current state is


as the sensors see it right now.
Introduction to

Artificial Intelligence
Table based agents
A table is simple way to specify a
mapping from percepts to actions.
Tables may become very large
All work done by the designer
No autonomy, all actions are predetermined
Learning may take a very long time
Mapping is implicity defined by a program
Rule based
Algorithmism
Introduction to

Artificial Intelligence
Percept based agent
Efficient
No internal representation for reasoning
inference.
No strategic planning, learning
Percept-based agents are not good for
multiple opposing goals.
Introduction to

Artificial Intelligence
State-based agents
Information come from censors –
percepts
The agents changes current state of the
world
Based on state of the world and
knowledge (memory), it triggers actions
through the effectors
Introduction to

Artificial Intelligence
Goal-based agents
Information come from censors –
percepts
Changes the agents current state of the
world
Based on state of the world and
knowledge (memory), and
goals/intentions, it chooses actions and
does them through the effectors
Introduction to

Artificial Intelligence
Goal based agents
Agent’s actions will depend upon its goal.
The sequence of steps required to solve
a problem is not known a priori and must
be determined by a systematic
exploration of the alternatives.
Introduction to

Artificial Intelligence
Utility-based Agent
A more general framework
Different preferences for different goals
A utility function maps a state or a
sequence of states to a real valued utility.
The agent acts so as to maximize
expected utility
Introduction to

Artificial Intelligence
Learning Agent
Learning allows an agent to operate in
initially unknown environment.
The learning element modifies the
performance element.
Learning is required for true autonomy
Introduction to

Artificial Intelligence

You might also like