In this type of game, the world consists in a chain of
rooms with potentially distractors rooms (i.e. leading to a dead end).
The agent stats on one end and has to collect a “coin” object which is
placed at the other end. There is no other objects present in the world
other than the coin to collect.
In this type of game, the agent spawns in a randomly generated maze and must find a specific object which is mentioned in the objective displayed when game starts. This is a text version of the task proposed in [Parisotto2017].
Emilio Parisotto and Ruslan Salakhutdinov. Neural map: Structured memory for deep reinforcement learning. arXiv:1702.08360, 2017.
A Simple Game¶
This simple game takes place in a typical house and consists in finding the right food item and cooking it.
Here’s the map of the house.
Bathroom + | + Bedroom +--+ Kitchen +----+ Backyard + + | | + + Living Room Garden