Scribd
Upload
32 views

Chapter 6 - Learning

This document outlines chapters for a course on fundamental artificial intelligence. It discusses topics like intelligent agents, problem solving, knowledge and reasoning, learning, communication and perception. It specifically covers forms of learning, components of a learning agent like the learning element, performance element and critic. It also discusses types of feedback, categories of learning like supervised, unsupervised and reinforcement learning, and inductive learning.

Uploaded by

somsonengda
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
32 views

Chapter 6 - Learning

This document outlines chapters for a course on fundamental artificial intelligence. It discusses topics like intelligent agents, problem solving, knowledge and reasoning, learning, communication and perception. It specifically covers forms of learning, components of a learning agent like the learning element, performance element and critic. It also discusses types of feedback, categories of learning like supervised, unsupervised and reinforcement learning, and inductive learning.

Uploaded by

somsonengda
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

1

2
Wollo University ,Kombolicha Institute of Technology

Department of Software Engineering

Fundamental of Artificial Intelligence

By Ashenafi Workie(MSc.)
KIOT@SE by Ashenafi Workie
Major chapters outlines

1 Chapter 1: Introduction to Artificial intelligence


2 Chapter 2: Intelligent Agent
3 Chapter 3: Solving Problems
4 Chapter 4: Knowledge and Reasoning
5 Chapter 5: Uncertain Knowledge and Reasoning
6 Chapter 6: Learning
7 Chapter 7:Communicating, Perceiving, and Acting 4
Learning
• Agent can improve their behavior through diligent study of their own
experiences.
• The idea behind learning is that percepts should be used not only for acting,
but also for improving the agent's ability to act in the future.
• Learning is essential for unknown environments
- i.e when designer lacks omniscience ( state of knowing everything)
• Learning is useful as a system construction method
- i.e expose the agent to reality rather than trying to write it
down
• Learning modifies the agent’s decision mechanisms to improve performance
5
Forms Learning
• A learning agent contains performance element that
is PEAS
• decides what actions to take
• a learning element that modifies the performance
element so that it makes better decisions.

Performance measure  Environment  Actuators  Sensors are abbreviated as PEAS


Percepts  Actions  Goal  Environment are abbreviated as PAGE

6
Learning agent
• It allows the agent to operate in unknown environment.
4 components:
1) Learning element.
2) Performance element.
3) Critic.
4) Problem generator.

7
Learning agent

• Learning element:
Responsible for making improvements.
• Performance element:
Responsible for selecting external action. (entire agent)-
Percepts and decides on action.
• Critic:
Learning element uses feedback from critic-how the agent is
doing, how the performance element should be modified to
do better in future.
8
Learning Agent

Figure: Learning Agent


9
Important components of learning agent
• Learning Element- responsible for making improvements
• Performance Element -responsible for selecting external action.
• Critic - designed to tell the learning element how well the agent is doing.
The critic employs a fixed standard of performance. Performance Standard
is a fixed measure that is conceptually outside the agent
• Problem Generator -responsible for suggesting actions that will lead to
new and informative experiences

10
Types of feedback
• Supervised learning: correct answers for each example
• Unsupervised learning: correct answers not given
• Reinforcement learning: occasional rewards

11
Learning Categories
• Supervised Learning- An agent can learn effects of it actions
through condition. Eg: Taxi Driver- instructor shouts “Brake”
• Unsupervised Learning-Involves learning patterns in the input
when no specific output values are supplied. Unsupervised agent
cannot learn what to do because it has no information as to what
constitutes a correct action or a desirable state.

12
Learning Categories
• Reinforcement Learning –Rather than being told what to do, a
reinforcement learning agent must learn from reinforcement.
Reinforcement learning includes the sub-problem of learning how the
environment works.
• Example:
• Chess game the reinforcement is received only at the end of the
game.
• In ping-pong, each point scored can be considered a reward; when
learning to crawl, any forward motion is an achievement .

13
Inductive Learning
• Inductive learning using a particular set of facts or ideas to form a general
principle.
• An algorithm for deterministic supervised learning is given as input the
correct value of the unknown function or for particular inputs and try to
recover something close to it.
• Simplest form: learn a function from examples

14
Inductive Learning
• Simplest form: learn a function from examples
f is the target function
An example is a pair (x, f(x))
Problem: find a hypothesis h such that h ≈ f
given a training set of examples
This is a highly simplified model of real learning:
• Ignores prior knowledge
• Assumes a deterministic, observable environment
• Assumes examples are given
• Assume that the agent wants to learn m f

15
End ….

16

You might also like