Policy Gradient Methods

This code shows how to do reinforcement learning with policy gradient methods. View the code for this example.

To run this example, you will need to install TensorFlow with GPU support (at least version 1.0.0) and a few other dependencies.

pip install gym[atari]
pip install tensorflow

Then install the package as follows.

cd ray/examples/policy_gradient/
python setup.py install

Then you can run the example as follows.

python ray/examples/policy_gradient/examples/example.py --environment=Pong-ram-v3

This will train an agent on the Pong-ram-v3 Atari environment. You can also try passing in the Pong-v0 environment or the CartPole-v0 environment. If you wish to use a different environment, you will need to change a few lines in example.py.