How to Automate Hyperparameter Tuning for Reinforcement Learning Agents

In this video I’m going to show you how to automate hyperparameter tuning for deep reinforcement learning models. This is a massive time saver when you’re trying to figure out a combination of hyperparameters for your agents.

All we need is the argparse module, and we can use the command line to pass in parameters for our agents. If we use the combination of these parameters as a file name, then we can keep track of which parameters have the biggest effect on our learning plots.

Then we just run multiple python commands with various parameters, take a nap, and come back to a series of experiments that tell us how to fine tune our agents.

Learn how to turn deep reinforcement learning papers into code:

Deep Q Learning:

Actor Critic Methods:

Curiosity Driven Deep Reinforcement Learning

Natural Language Processing from First Principles: Learning Fundamentals

Here are some books / courses I recommend (affiliate links):
Grokking Deep Learning in Motion:
Grokking Deep Learning:
Grokking Deep Reinforcement Learning:

Come hang out on Discord here:


Source of this AI Video

AI video(s) you might be interested in …