islamia university of BWP
Presented by Muhammad Faheem
INTRODUCTION
Reinforcement Learning is a type of machine learning where
an agent learns how to make decisions by performing
actions in an environment and receiving feedback in the
form of rewards or penalties. The goal is to learn a strategy
(policy) to maximize the cumulative reward over time.
WHAT IS
REINFORCEMENT
LEARNING ?
Define Reinforcement Learning:
"A branch of machine learning where agents learn by
interacting with an environment to maximize cumulative
rewards."
Brief mention of its importance and applications:
Robotics, gaming, recommendation systems,
autonomous vehicles.
KEY CONCEPT
Agent
Environment
State
Action
Reward
Policy
Agent: The learner or decision-maker.
Environment: Everything the agent interacts with.
Action: What the agent can do.
State: The current situation of the agent in the
environment.
Reward: Feedback from the environment based on
the agent's actions.
Policy: The strategy the agent uses to determine
actions.
Value Function: Predicts the long-term reward of a
state.
TYPES
REINFORCEMEN Model-Free RL
T LEARNING ? Model-Based RL
APPLICATIONS OF RL
Robotics: Training robots for tasks like
assembly or navigation
Gaming: AlphaGo, OpenAI’s Dota 2 bot.
Healthcare: Personalized treatment
recommendations.
Finance: Portfolio management and
trading strategies.
QUESTIONS
AND ANSWER