PyGame Learning Environment

class tensorforce.environments.PyGameLearningEnvironment(level, visualize=False, frame_skip=1, fps=30)[source]

PyGame Learning Environment environment adapter (specification key: ple, pygame_learning_environment).

May require:

sudo apt-get install git python3-dev python3-setuptools python3-numpy python3-opengl \
libsdl-image1.2-dev libsdl-mixer1.2-dev libsdl-ttf2.0-dev libsmpeg-dev  libsdl1.2-dev \
libportmidi-dev libswscale-dev libavformat-dev libavcodec-dev libtiff5-dev libx11-6 \
libx11-dev fluid-soundfont-gm timgm6mb-soundfont xfonts-base xfonts-100dpi xfonts-75dpi \
xfonts-cyrillic fontconfig fonts-freefont-ttf libfreetype6-dev

pip install git+

pip install git+
  • level (string | subclass of – Game instance or name of class in, like ‘doom’, ‘flappybird’, ‘monsterkong’, ‘catcher’, ‘pixelcopter’, ‘pong’, ‘puckworld’, ‘raycastmaze’, ‘snake’, ‘waterworld’ (required).
  • visualize (bool) – Whether to visualize interaction (default: false).
  • frame_skip (int > 0) – Number of times to repeat an action without observing (default: 1).
  • fps (int > 0) – The desired frames per second we want to run our game at (default: 30).