Python Jupyter Notebook
Switch branches/tags
Nothing to show
Clone or download

README.md

Deep Reinforcement Learning

Codacy Badge

This code is part of my master thesis at the VUB, Brussels.

Status

Different algorithms have currently been implemented:

Asynchronous Advantage Actor Critic (A3C)

The code for this algorithm can be found here. Example run after training using 16 threads for a total of 5 million timesteps on the PongDeterministic-v4 environment:

Pong example run

How to run

First, install the requirements using pip (you can first remove OpenCV from the requirements.txt file if it is already installed):

pip install -r requirements.txt

Algorithms/experiments

You can run algorithms by passing the path to an experiment specification (which is a file in json format) to main.py:

python main.py <path_to_experiment_specification>

Examples of experiment specifications can be found in the experiment_specs folder.

Statistics

Statistics can be plot using:

python misc/plot_statistics.py <path_to_stats>

<path_to_stats> can be one of 2 things:

  • A json file generated using gym.wrappers.Monitor, in case it plots the episode lengths and total reward per episode.
  • A directory containing TensorFlow scalar summaries for different tasks, in which case all of the found scalars are plot.

Help about other arguments (e.g. for using smoothing) can be found by executing python misc/plot_statistics.py -h.

Alternatively, it is also possible to use Tensorboard to show statistics in the browser by passing the directory with the scalar summaries as --logdir argument.