Evolutionary computation provides methods to automatically generate controllers for swarm robotics. Many approaches rely on optimization and the targeted behavior is quantified in form of a fitness function. Other methods, like novelty search, increase exploration by putting selective pressure on unexplored behavior space using a domain-specific behavioral distance function. In contrast, minimize surprise leads to the emergence of diverse behaviors by using an intrinsic motivation as fitness, that is, high prediction accuracy. We compare a standard genetic algorithm, novelty search and minimize surprise in a swarm robotics setting to evolve diverse behaviors and show that minimize surprise is competitive to novelty search.
|Title of host publication||GECCO '20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion|
|Number of pages||2|
|Publisher||Association for Computing Machinery|
|Publication status||Published - 08.07.2020|
|Event||2020 Genetic and Evolutionary Computation Conference - Cancun, Mexico|
Duration: 08.07.2020 → 12.07.2020
Conference number: 161684