Modern Reinforcement Learning: Deep Q Learning in PyTorch

Modern Reinforcement Learning: Deep Q Learning in PyTorch ranks 2nd in the list of best online PyTorch courses. Deep Reinforcement Learning Research papers can be turned into agents that can beat classic Atari games. You will learn a repeatable framework for reading and implementing deep reinforcement learning research papers in this PyTorch course. The original papers that introduced Deep Q learning, Double Deep Q learning, and Dueling Deep Q learning algorithms will be read.

You'll also learn how to implement these in pythonic, concise PyTorch code that can be extended to include any future deep Q learning algorithms. These algorithms will be used to solve a variety of Pong, Breakout, and Bank Heist environments from the Open AI gym's Atari library. Finally, you will learn the key to making these Deep Q Learning algorithms work, which is how to modify the Open AI Gym's Atari library to meet the specifications of the original Deep Q Learning papers.

In this course, you will learn how to:

• read and implement deep reinforcement learning papers.
• code Deep Q learning agents.
• code Double Deep Q Learning Agents.
• code Dueling Deep Q and Dueling Double Deep Q Learning Agents.
• write modular and extensible deep reinforcement learning software.
• automate hyperparameter tuning with command line arguments.
• repeat actions to reduce computational overhead
• rescale the Atari screen images to increase efficiency
• stack frames to give the Deep Q agent a sense of motion
• evaluate the Deep Q agent's performance with random no-ops to deal with the model overtraining

You can take the Modern Reinforcement Learning: Deep Q Learning in PyTorch certification course on Udemy.

Course rating: 4.6 out of 5.0

Duration: 5 h 5 m

Certificate: Certificate on completion

Enroll here: udemy.com/course/deep-q-learning-from-paper-to-code