inoryy / tensorflow2-deep-reinforcement-learning

Code accompanying the blog post "Deep Reinforcement Learning with TensorFlow 2.1"
http://inoryy.com/post/tensorflow2-deep-reinforcement-learning/
MIT License
207 stars 50 forks source link
a2c advantage-actor-critic deep-reinforcement-learning keras tensorflow tensorflow2

Deep Reinforcement Learning with TensorFlow 2.1

Source code accompanying the blog post Deep Reinforcement Learning with TensorFlow 2.1.

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, a self-contained script, or execute it online with Google Colab.

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, e.g. python a2c.py --batch_size=256.