https://github.com/inoryy/tensorflow2-deep-reinforcement-learning

Code accompanying the blog post "Deep Reinforcement Learning with TensorFlow 2.1"
https://github.com/inoryy/tensorflow2-deep-reinforcement-learning

a2c advantage-actor-critic deep-reinforcement-learning keras tensorflow tensorflow2

Last synced: 2 days ago
JSON representation

Code accompanying the blog post "Deep Reinforcement Learning with TensorFlow 2.1"

• Host: GitHub
• URL: https://github.com/inoryy/tensorflow2-deep-reinforcement-learning
• Owner: inoryy
• License: mit
• Created: 2019-01-19T20:42:29.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2021-08-12T19:39:54.000Z (about 3 years ago)
• Last Synced: 2024-10-27T18:57:38.487Z (9 days ago)
• Topics: a2c, advantage-actor-critic, deep-reinforcement-learning, keras, tensorflow, tensorflow2
• Language: Jupyter Notebook
• Homepage: http://inoryy.com/post/tensorflow2-deep-reinforcement-learning/
• Size: 94.7 KB
• Stars: 207
• Watchers: 10
• Forks: 50
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-tensorflow-2 - Deep Reinforcement Learning with TensorFlow 2.0

README

        
# Deep Reinforcement Learning with TensorFlow 2.1

Source code accompanying the blog post

[Deep Reinforcement Learning with TensorFlow 2.1](http://inoryy.com/post/tensorflow2-deep-reinforcement-learning/).

In the blog post, I showcase the `TensorFlow 2.1` features through the lens of deep reinforcement learning

by implementing an advantage actor-critic agent, solving the classic `CartPole-v0` environment.

While the goal is to showcase `TensorFlow 2.1`, I also provide a brief overview of the DRL methods.

You can view the code either as a [notebook](actor-critic-agent-with-tensorflow2.ipynb),

a self-contained [script](a2c.py), or execute it online with

[Google Colab](https://colab.research.google.com/drive/1XoHmGiwo2eUN-gzSVLRvE10fIf_ycO1j).

To run it locally, install the dependencies with `pip install -r requirements.txt`, and then execute `python a2c.py`.  

To control various hyperparameters, specify them as [flags](https://github.com/inoryy/tensorflow2-deep-reinforcement-learning/blob/master/a2c.py#L12-L17), e.g. `python a2c.py --batch_size=256`.