Scribd
Upload
6 views

Reinforcement Learning

Uploaded by

Nivi 1702
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
6 views

Reinforcement Learning

Uploaded by

Nivi 1702
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Reinforcement

Learning

By: Niveditha Haridas


Course: MBA Business Analytics
Roll no: 2302032
Subject: Business Analytics & Data Science
Subject Code: KMBA 106
Introduction
Reinforcement learning (RL) is a type of machine
learning where an agent learns to make decisions
by interacting with an environment. The agent
receives feedback in the form of rewards or
penalties, which helps it learn the optimal strategy
to achieve its goals.

RL is used in various applications such as game


playing, robotics, and autonomous driving.
History of Reinforcement
Learning
• Reinforcement learning (RL) originated in the 1930s from the study of positive reinforcement
and animal behaviorism. Behavioral psychologist B. F. Skinner demonstrated that animals
could be trained to perform complex tasks through simple reinforcement mechanisms.
• Early concepts of RL emerged in the mid-20th century, primarily influenced by psychological
theories of operant conditioning. The term reinforcement was introduced by Pavlov in 1903.
• RL is a machine learning training method based on rewarding desired behaviors and punishing
undesired ones. The agent is rewarded for correct moves and punished for the wrong ones. In
doing so, the agent tries to minimize wrong moves and maximize the right ones.
Main points in
Reinforcement learning
• Input: The input should be an initial state from which the model will
start
• Output: There are many possible outputs as there are a variety of
solutions to a particular problem
• Training: The training is based upon the input, The model will return
a state and the user will decide to reward or punish the model based
on its output.
• The model keeps continues to learn.
• The best solution is decided based on the maximum reward.
Reinforcement learning Supervised learning

Reinforcement learning is all about making decisions


sequentially. In simple words, we can say that the output In Supervised learning, the decision is made on the initial
depends on the state of the current input and the next input input or the input given at the start
depends on the output of the previous input

In Reinforcement learning decision is dependent, So we give In supervised learning the decisions are independent of each
labels to sequences of dependent decisions other so labels are given to each decision.

Example: Chess game,text summarization Example: Object recognition,spam detetction


Types of Reinforcement Learning
There are two types of Reinforcement:

• Positive: Positive Reinforcement is • Negative: Negative


defined as when an event, occurs due Reinforcement is defined as
to a particular behavior, increases the strengthening of behavior
strength and the frequency of the because a negative condition is
behavior. In other words, it has a stopped or avoided.
positive effect on behavior.
Application of Reinforcement
Learnings
• RL can be used in robotics for industrial automation.
• RL can be used in machine learning and data processing
• RL can be used to create training systems that provide
custom instruction and materials according to the
requirement of students.
Advantages of Reinforcement
learning
• Reinforcement learning can be used to solve very complex problems that
cannot be solved by conventional techniques.
• The model can correct the errors that occurred during the training process.
• In RL, training data is obtained via the direct interaction of the agent with the
environment
• Reinforcement learning can handle environments that are non-deterministic,
meaning that the outcomes of actions are not always predictable.
Disdvantages of Reinforcement
learning
• Reinforcement learning is not preferable to use for solving simple problems.
• Reinforcement learning needs a lot of data and a lot of computation
• Reinforcement learning is highly dependent on the quality of the reward
function. If the reward function is poorly designed, the agent may not learn
the desired behavior.
• Reinforcement learning can be difficult to debug and interpret.

You might also like