Reinforcement learning of iterative behaviour with multiple sensors

摘要

Reinforcement learning allows an agent to be both reactive and adaptive, but it requires a simple yet consistent representation of the task environment. In robotics this representation is the product of perception. Perception is a powerful simplifying mechanism because it ignores much of the complexity of the world by mapping multiple world states to each of a few representational states. The constraint of consistency conflicts with simplicity, however. A consistent representation distinguishes world states that have distinct utilities, but perception systems with sufficient acuity to do this tend to also make many unnecessary distinctions.