Deep Reinforcement Learning

Welcome to the Deep Reinforcement Learning Nanodegree program!

You are starting a challenging but rewarding journey! Take 5 minutes to read how to get help with projects and content.

Obtain helpful resources to accelerate your learning in this first part of the Nanodegree program.

Reinforcement learning is a type of machine learning where the machine or software agent learns how to maximize its performance at a task.

Learn how to mathematically formulate tasks as Markov Decision Processes.

In reinforcement learning, agents learn to prioritize different decisions based on the rewards and punishments associated with different outcomes.

Write your own implementation of Monte Carlo control to teach an agent to play Blackjack!

Learn about how to apply temporal-difference methods such as SARSA, Q-Learning, and Expected SARSA to solve both episodic and continuing tasks.

With reinforcement learning now in your toolbox, you're ready to explore a mini project using OpenAI Gym!

Learn how to adapt traditional algorithms to work with continuous spaces.

In the next parts of the Nanodegree program, you'll learn all about how to use neural networks as powerful function approximators in reinforcement learning.

This lesson covers the study plan and prerequisites for this course.

Extend value-based reinforcement learning methods to complex problems using deep neural networks.

Obtain helpful resources to accelerate your learning in the third part of the Nanodegree program.

Policy-based methods try to directly optimize for the optimal policy.

Policy gradient methods search for the optimal policy through gradient ascent.

Learn what Proximal Policy Optimization (PPO) is and how it can improve policy gradients. Also learn how to implement the algorithm by training a computer to play the Atari Pong game.

Miguel Morales explains how to combine value-based and policy-based methods, bringing together the best of both worlds, to solve challenging reinforcement learning problems.

Learn how to apply deep reinforcement learning techniques for optimal execution of portfolio transactions.

Obtain helpful resources to accelerate your learning in the fourth part of the Nanodegree program.

The dynamic programming setting is a useful first step towards tackling the reinforcement learning problem.

Review the basics of neural networks.

Review the basics of convolutional neural networks.

Learn how to use PyTorch for building deep learning models.

Learn how to use Workspaces in the Udacity classroom.

The differences between C++ and Python and how to write C++ code.

To program matrix algebra operations and translate your Python code, you will need to use C++ Vectors. These vectors are similar to Python lists, but the syntax can be somewhat tricky.

Learn how to write C++ code on your own computer and compile it into a executable program without running into too many compilation errors.

Learn the syntax of C++ object oriented programming as well as some of the additional OOP features provided by the language.

In this lesson, we'll compare the execution times of C++ and Python programs.

Optimizing C++ involves understanding how a computer actually runs your programs. You'll learn how C++ uses the CPU and RAM to execute your code and get a sense for what can slow things down.

Now you understand how C++ programs execute. It's time to learn specific optimization techniques and put them into practice. This lesson will prepare you for the lesson's code optimization project.

Get ready to optimize some C++ code. You are provided with a working 2-dimensional histogram filter; your job is to get the histogram filter code to run faster!