Deep Q-Learning Network From Scratch in Python, TensorFlow, and OpenAI Gym - Part 1- Reinforcement

preview_player
Показать описание
#reinforcementlearning #machinelearning #deepqlearning #dqn #controlengineering #datascience #controltheory #qlearning #openaigym #openai
It takes a significant amount of time and energy to create these free video tutorials. You can support my efforts in this way:
- You Can also press the Thanks YouTube Dollar button

The webpage accompanying this tutorial is given here:

THIS IS THE FIRST PART!

In this reinforcement learning tutorial, we explain the basics of the deep Q learning network reinforcement learning algorithm. We explain how to implement this algorithm in Python by using the TensorFlow library. We perform tests in the OpenAI Gym Cart-Pole environment.
Рекомендации по теме
Комментарии
Автор

It takes a significant amount of time and energy to create these free video tutorials. You can support my efforts in this way:
- You Can also press the Thanks YouTube Dollar button

aleksandarhaber
Автор

You are doing awesome work. Thank you for sharing this resource.

PanicGiraffe
Автор

I have no idea how to thank you. I was scared of reinforcement learning and watched a lot of tutorials but these are the ones that actually we into my head. You explained those complex ideas in a less scary way.

nabilanoor
Автор

Thanks for sharing this video with us ❤

aasheesh
Автор

Is it also possible to do this when action space is continuous (without discretizing action space)? Maximizing over the action might be inefficient or is there some trick to do this?

id-icou
join shbcf.ru