This course on reinforcement learning aims to provide a solid foundation in core topics such as Q learning, SARSA, double Q learning, deep Q learning, and policy gradient methods. By using environments from the OpenAI gym and tools like Tensorflow and PyTorch, learners will acquire skills in coding and implementing these algorithms. The teaching method involves a combination of theoretical explanations, coding tutorials, and practical demonstrations. This course is intended for individuals interested in machine learning, specifically reinforcement learning, and those looking to understand and apply algorithms to maximize rewards in various scenarios.
Overview
Syllabus
Intro .
Intro to Deep Q Learning .
How to Code Deep Q Learning in Tensorflow .
Deep Q Learning with Pytorch Part 1: The Q Network .
Deep Q Learning with Pytorch part 2: Coding the Agent .
Deep Q Learning with Pytorch part.
Intro to Policy Gradients 3: Coding the main loop .
How to Beat Lunar Lander with Policy Gradients .
How to Beat Space Invaders with Policy Gradients .
How to Create Your Own Reinforcement Learning Environment Part 1 .
How to Create Your Own Reinforcement Learning Environment Part 2 .
Fundamentals of Reinforcement Learning .
Markov Decision Processes .
The Explore Exploit Dilemma .
Reinforcement Learning in the Open AI Gym: SARSA .
Reinforcement Learning in the Open AI Gym: Double Q Learning .
Conclusion .
Taught by
freeCodeCamp.org
Related Courses
-
Python Reinforcement Learning using OpenAI Gymnasium – Full Course
-
Modern Reinforcement Learning: Deep Q Learning in PyTorch
-
Reinforcement Learning Course: Intro to Advanced Actor Critic Methods
-
Machine Learning
5.0 -
Advanced AI: Deep Reinforcement Learning in Python
-
Deep Reinforcement Learning
5.0
Related articles
Reviews
5.0 rating, based on 1 Class Central review
-
Reinforcement Learning (RL) is a machine learning (ML) technique to learn sequential decision-making in complex problems. RL is inspired by trial-and-error based human/animal learning. It can learn an optimal policy autonomously with knowledge obtained by continuous interaction with a stochastic dynamical environment
