To address these challenges, we built our Neural MMO to meet the following criteria:

Players (agents) may join any available server (environment), each containing an automatically generated tile-based game map of configurable size. Some tiles, such as food-bearing forest tiles and grass tiles, are traversable. Others, such as water and solid stone, are not. Agents spawn at a random location along the edges of the environment. They must obtain food and water, and avoid combat damage from other agents, in order to sustain their health. Stepping on a forest tile or next to a water tile refills a portion of the agent’s food or water supply, respectively. However, forest tiles have a limited supply of food, which regenerates slowly over time. This means that agents must compete for food tiles while periodically refilling their water supply from infinite water tiles. Players engage in combat using three combat styles, denoted Melee, Range, and Mage for flavor.

Input: Agents observe a square crop of tiles centered on their current position. This includes tile terrain types and the select properties (health, food, water, and position) of occupying agents.

Output: Agents output action choices for the next game tick (timestep). Actions consist of one movement and one attack.