Scribd
Upload
1 views

RL Machine Learning

Uploaded by

eiragefatima999
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
1 views

RL Machine Learning

Uploaded by

eiragefatima999
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 6

💡REINFORCEMENT

LEARNING

Presented By : Eshwar &


Areeba 🐱‍🏍
REINFORCEMENT
LEARNING
🐋Multiple definitions; for quick understanding :)
• RL is a branch of machine learning focused on making decisions to maximize
cumulative rewards in a given situation.
• focuses on how agents should take actions in an environment to maximize
cumulative rewards.
• Mapping form state(environment) to actions.
• Train itself in order to gain optimal results.
• RL is autonomous, self-teaching system learn by trial and error.
• It uses reward-punishment paradigm as they process data.
🔑KEY CONCEPT OF
REINFORCEMENT LEARNING
• Agent: The learner or decision-
maker.
• Environment: Everything the
agent interacts with.
• State: A specific situation in
which
the agent finds itself.
• Action: All possible moves the
agent can make.
• Reward: Feedback from the
environment based on the
action taken.
👍 Pros Policy
• solve very complex problems. • A strategy used by the agent to
• data trained directly from determine the next action based
environment. on the current state.
• correct errors during training
process.
Q-value
👎 Consnon-deterministic
• handle • Represents the expected reward of
• evnironment.
can’t solve simple problem. taking a particular action from a
• require lots of data and specific state.
computation.
• highly dependent on reward
function.
APPLICATIONS OF RL
• Self-Driving Cars
• Game AI
• Robotics
Exploration: refers to trying out new
actions to discover their potential
rewards, even if they aren't
immediately beneficial.

Exploitation: involves choosing the


action that currently provides the
highest known reward based on past
experiences.

You might also like