Skip to content
This repository has been archived by the owner on Oct 20, 2022. It is now read-only.

In this repository, we share the code for our blog post on reinforcement learning with TF-Agents to play doom with PPO.

Notifications You must be signed in to change notification settings

arconsis/blog-playing-doom-with-tf-agents

Repository files navigation

Examples for Applied Reinforcement Learning: Playing Doom with TF-Agents and PPO

In this repository, we provide the code for our tutorial on applied reinforcement learning. We utilize TensorFlow's TF-Agents library to build a neural network agent capable of playing the video game Doom from pixels. To train the agent, Proximal Policy Optimization (PPO) is used.

For more details, have a look at our article.

Repository Contents

This repository contains the following main components:

  • ppo_train_eval_doom_simple.py: A minimal example on how to train Doom with TF-Agents and PPO.
  • ppo_train_eval_doom_extended.py: A full example on how to train Doom with TF-Agents and PPO. This also includes logging metrics of training performance with TensorBoard and saving checkpoints.
  • doom/DoomEnvironment.py: An implementation of TF-Agents' PyEnvironment mapping running a vizdoom instance and mapping actions and the observations for our agent.
  • basic.cfg: Configuration for the basic Doom scenario with adaptions to work with our setup.

Installation

Please refer to our instructions in the article.

About

In this repository, we share the code for our blog post on reinforcement learning with TF-Agents to play doom with PPO.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages