Evaluating Long-Term Memory in 3D Mazes

Understand

Intelligent agents need to remember salient information to reason in partially-observed environments.

• For example, agents with a first-person view should remember the positions of relevant objects even if they go out of view.
• Similarly, to effectively navigate through rooms agents need to remember the floor plan of how rooms are connected.
• However, most benchmark tasks in reinforcement learning do not test long-term memory in agents, slowing down progress in this important research direction.