GVGAI GYM

An OpenAI Gym environment for games written in the Video Game Description Language, including the Generic Video Game Competition framework.

The framework, along with some initial reinforcement learning results, is covered in the paper Deep Reinforcement Learning for General Video Game AI. This paper should be cited if code from this project is used in any way:

@inproceedings{torrado2018deep,
  title={Deep Reinforcement Learning for General Video Game AI},
  author={Torrado, Ruben Rodriguez and Bontrager, Philip and Togelius, Julian and Liu, Jialin and Perez-Liebana, Diego},
  booktitle={Computational Intelligence and Games (CIG), 2018 IEEE Conference on},
  year={2018},
  organization={IEEE}
}

Installation

Usage

Demo video on YouTube

Once installed, it can be used like any OpenAI Gym environment.

Run the following line to get a list of all GVGAI environments.

[env.id for env in gym.envs.registry.all() if env.id.startswith('gvgai')]

Contributing

Bug reports and pull requests are welcome on GitHub at https://github.com/rubenrtorrado/GVGAI_GYM.

License

This code is available as open source under the terms of the Apache License 2.0.

GVGAI Single-Player Competition @CIG18

The 2nd GVGAI Single-Player Competition will be organised at the IEEE’s 2018 Conference on Computational Intelligence and Games (CIG18).

Important notice: A new GVGAI-Gym will be used in this competition from last year. The competition rules have been changed.

Rules

Due to the long training time, the GVGAI server won’t be used for training your agent. Please train your agent using your own machine or server.

Preparation

Download and set up the new GVGAI-Gym framework on your machine/server.

Demo video on YouTube

Training Phase (NOW - 3 July 2018)

Program your agent and train it

Validation Phase (4 - 29 July 2018)

The released game are named as:

Submission

Remark: no feedback will be given until the bug report phase will start.

Bug Report Phase

Validation Phase

Your agent will play the same games (G1, G2 and G3) that we have released for training, multiple times, but on private levels. At this phase, your agent should return a legal action in no more than 100ms per game tick.

Timeline

Resources

GVGAI website

GVGAI-Gym (master branch)

Demo video on YouTube