Architectures that Handle Lots of Knowledge

Many real world and simulated environments are rich in detail and other information. The ability to incrementally add knowledge without significant slowdown is important for agents in these environments to function.

This information can be difficult or impossible to capture during development, so learning is frequently employed to capture domain knowledge as the agent experiences its environment.

The following architectures were designed to operate in a knowledge-rich environment:


Back to List of Other Environmental Characteristics