Welcome to the MARLO wiki!

MARLO (short for Multi-Agent Reinforcement Learning in MalmO) is an Artificial Intelligence competition primarily aimed towards the goal of implementing reinforcement learning agents with a great degree of generality, capable of solving problems in pseudo-random, procedurally changing multi-agent environments within the world of the mediatic phenomenon game Minecraft.

Marlo is based off of the Malmo framework, which is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. The Malmo platform provides a high-level API which enables access to actions, observations (i.e. location, surroundings, video frames, game statistics) and other general data that Minecraft provides. Marlo, on the other hand, is a wrapper for Malmo that provides a more standardized RL-friendly environment for scientific study.

The framework is written as an extension to OpenAI's Gym framework, which is a toolkit for developing and comparing reinforcement learning algorithms, thus providing an industry-standard and familiar platform for scientists, developers and popular RL frameworks.

Please follow the links below to find the instructions for installing, running and submitting agents to the MARLO Competition:

• Installation Instructions
• Creating MARLO Agents
• Submit

If you have found any problems with the framework or any of these steps, please open an issue on this repository: https://github.com/crowdAI/marLo/issues

You can also check our Troubleshooting page for common errors during the installation / execution process.

For any other query, please email Diego Perez or Sharada Mohanty.

You can also visit our competition page.