ViZDoom Library in Reinforcement Learning

Posted on Edited on In Views:

Sources:

  1. --> Documentation
  2. --> Turorial

ViZDoom allows developing AI bots that play Doom using only visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular.

Install

On Linux:

1
pip install vizdoom

Tested on Ubuntu22.04 X86_64 with python=3.9.

Scripts

--> A lot of example scripts, including:

  1. examples/python/basic.py: The basic script, where the agent will perform random actions.
  2. examples/python/spectator.py: The script of playing ViZDoom by yourself (as human), instead of by conducting random actions

Play ViZDoom by yourself:

1
2
3
git clone [email protected]:Farama-Foundation/ViZDoom.git
cd ViZDoom
python examples/python/basic.py