Quality Diversity Through Surprise
share
Quality diversity is a recent evolutionary computation paradigm which maintains an appropriate balance between divergence and convergence and has achieved promising results in complex problems. There is, however, limited exploration on how different paradigms of divergent search may impact the solutions found by quality diversity algorithms. Inspired by the notion of surprise as an effective driver of divergent search and its orthogonal nature to novelty this paper investigates the impact of the former to quality diversity performance. For that purpose we introduce three new quality diversity algorithms which use surprise as a diversity measure, either on its own or combined with novelty, and compare their performance against novelty search with local competition, the state of the art quality diversity algorithm. The algorithms are tested in a robot maze navigation task, in a challenging set of 60 deceptive mazes. Our findings suggest that allowing surprise and novelty to operate synergistically for divergence and in combination with local competition leads to quality diversity algorithms of significantly higher efficiency, speed and robustness.
READ FULL TEXT
