Fundamentals of reinforcement learning
Reinforcement Learning with Gymnasium in Python
Fouad Trad
Machine Learning Engineer
Reinforcement learning
Agent learns through trial and error
Reinforcement learning
Agent learns through trial and error
Reinforcement learning
Agent learns through trial and error
Reinforcement learning
Agent learns through trial and error
Agent receives:
Rewards for good decisions
Penalties for bad decisions
Goal
: maximize positive feedback over time
RL as training a pet
RL vs. other ML types
RL vs. other ML types
RL vs. other ML types
When to use RL?
Sequential decision-making
Decisions influence future observations
Learning through rewards and penalties
No direct supervision
Appropriate for RL: playing video games
Player makes sequential decisions
Receives points and loses lives depending on actions
Inappropriate for RL: in-game object recognition
No sequential decision-making
No interaction with an environment
RL applications
Robotics
Robot walking
Object manipulation
RL applications
Robotics
Robot walking
Object manipulation
Finance
Optimizing trading and investment
Maximize profit
RL applications
Autonomous Vehicles
Enhancing safety and efficiency
Minimizing accident risks
RL applications
Autonomous Vehicles
Enhancing safety and efficiency
Minimizing accident risks
Chatbot development
Enhancing conversational skills
Improving user experiences
What's next?
In this course we will:
Understand RL foundations and principles
Identify, frame, and solve RL problems
Application with Gymnasium
Let's practice!
Reinforcement Learning with Gymnasium in Python
Preparing Video For Download...