Intelligent agent - Artifical Intelligence

PPT deals with AI agents

1. Intelligent Agents

2. Components of AI Agents
*Perception*: AI agents perceive their environment
through sensors, which could include cameras,
microphones, or other types of sensors depending on the
application.
*Reasoning*: AI agents use reasoning mechanisms to
process information, make decisions, and plan actions to
achieve their goals.
*Actuation*: AI agents act upon their environment through
actuators, which could include motors, displays, or other
mechanisms to interact with the physical or virtual world.
Artificial Intelligence a modern approach
2

3. Agents
Artificial Intelligence a modern approach
3
Agent denotes rather generally a system that
processes information and produces an output
from an input.
In classical computer science, software agents are
primarily employed . In this case the agent consists
of a program that calculates a result from user
input.
In robotics, on the other hand, hardware agents
(also called autonomous robots) are employed,
which additionally have sensors and actuators at
their disposal

4. Agents
Artificial Intelligence a modern approach
4

5. Agents
Artificial Intelligence a modern approach
5
•An agentis anything that can be viewed as
perceivingits environmentthrough sensorsand
actingupon that environment through actuators
With the actuators it carries out actions and
changes its environment.
•Human agent:
–eyes, ears, and other organs for sensors;
–hands, legs, mouth, and other body parts for actuators
•Robotic agent:
–cameras and infrared range finders for sensors
–various motors for actuators

6. Agents and environments
Artificial Intelligence a modern approach
6
•The agentfunctionmaps from percept histories to
actions:
[f: P*A]
•The agentprogramruns on the physical architectureto
produce f
•agent = architecture + program

7. Agent types
Artificial Intelligence a modern approach
7
Four basic types in order of increasing generality:
Simple reflex agents
Reflex agents with state/model
Goal-based agents
Utility-based agents
All these can be turned into learning agents

8. Simple reflex agents
Artificial Intelligence a modern approach
8

9. Simple reflex agents
Artificial Intelligence a modern approach
9
Simple but very limited intelligence.
Action does not depend on percept history, only on
current percept.
Therefore no memory requirements.
Infinite loops
Suppose vacuum cleaner does not observe location. What
do you do given location = clean? Left of A or right on B -
> infinite loop.

10. Characteristics of Reflex Agent
Reactive:Reacts directly to current sensory input without
considering past experiences or future consequences.
Limited Scope:Capable of handling simple tasks or
environments with straightforward cause-and-effect
relationships.
Fast Response:Makes quick decisions based solely on
the current state, leading to rapid action execution.
Lack of Adaptability:Unable to learn or adapt based on
feedback, making it less suitable for dynamic or changing
environments.
Artificial Intelligence a modern approach
10

11. States: Beyond Reflexes
•Recall the agentfunctionthat maps from percept histories
to actions:
[f: P*A]
An agent program can implement an agent function by
maintaining an internal state.
The internal state can contain information about the state
of the external environment.
The state depends on the history of percepts and on the
history of actions taken:
[f: P*, A*SA] where Sis the set of states.
If each internal state includes all information relevant to
information making, the state space is Markovian.
Artificial Intelligence a modern approach
11

12. Model-based reflex agents
Artificial Intelligence a modern approach
12

13. Model Based Reflex Agents
Characteristics Model-Based Reflex Agents
Adaptive:Maintains aninternal modelof the environment to
anticipate future states and make informed decisions.
Contextual Understanding:Considers both current input and
historical data to determine appropriate actions, allowing for more
nuanced decision-making.
Computational Overhead: Requires resources to build, update, and
utilize the internal model, leading to increased computational
complexity.
Improved Performance: Can handle more complex tasks and
environments compared to simple reflex agents, thanks to its ability to
incorporate past experiences.
Artificial Intelligence a modern approach
13

14. Goal-based agents
Artificial Intelligence a modern approach
14
•knowing state and environment? Enough?
–Taxi can go left, right, straight
•Have a goal
A destination to get to
Uses knowledge about a goal to guide its actions
E.g., Search, planning
A mobile robot which should move from room 112 to room 179 in a
building takes actions different from those of a robot that should move
to room 105. In other words, the actions depend on the goal. Such
agents are called goal-based agents.

15. Goal-based agents
Artificial Intelligence a modern approach
15
•Reflex agent breaks when it sees brake lights. Goal based agent
reasons
–Brake light -> car in front is stopping -> I should stop -> I should use brake

16. Application of AI Agents
Autonomous Vehicles*: Self-driving cars use AI agents to perceive the
environment (through sensors), reason about their surroundings, and
make decisions to navigate safely and efficiently.
Robotics*: Robots use AI agents to interact with their environment,
perform tasks, and adapt to changing conditions.
*Virtual Assistants*: AI agents like Siri, Alexa, and Google Assistant use
natural language processing and machine learning to understand user
queries and provide relevant responses.
*Game Playing*: AI agents are used in games to act as opponents (e.g.,
chess-playing agents) or teammates (e.g., in multiplayer online games).
Artificial Intelligence a modern approach
16