Modulating Perception with Pleasure for Action Selection

Persistence and opportunism are two key features of cognitive action selection architectures. For an autonomous robot that has to satisfy multiple conflicting survival-related needs, it is crucial to persist in the execution of behaviors for long enough to get sufficient benefit. Persistence is important to avoid what is known as the "dithering" problem, which occurs when a robot keeps switching between trying to satisfy two needs without satisfying either of them enough to guarantee survival. Opportunism concerns the initiation of actions, and occurs when an agent chooses to consume a resource that might not satisfy its most pressing need, but which is available now and might not be available later. The degree to which a robot should show persistence and opportunism depends on multiple factors; we could generally say that persistence leads to a more "conservative" action selection behavior and opportunism to a more "risky" one.