Increasing Behavioral Complexity for Evolved Virtual Creatures with the ESP Method
This addresses a long-standing problem in evolutionary computation and artificial life for researchers, though it is incremental as it builds on existing EVC frameworks.
The paper tackles the stagnation in behavioral complexity of evolved virtual creatures (EVCs) by introducing the ESP method, which uses a syllabus of intermediate tasks and mechanisms for task preservation and combination, resulting in approximately doubling the previous state-of-the-art behavioral complexity.
Since their introduction in 1994 (Sims), evolved virtual creatures (EVCs) have employed the coevolution of morphology and control to produce high-impact work in multiple fields, including graphics, evolutionary computation, robotics, and artificial life. However, in contrast to fixed-morphology creatures, there has been no clear increase in the behavioral complexity of EVCs in those two decades. This paper describes a method for moving beyond this limit, making use of high-level human input in the form of a syllabus of intermediate learning tasks--along with mechanisms for preservation, reuse, and combination of previously learned tasks. This method--named ESP for its three components: encapsulation, syllabus, and pandemonium--is presented in two complementary versions: Fast ESP, which constrains later morphological changes to achieve linear growth in computation time as behavioral complexity is added, and General ESP, which allows this restriction to be removed when sufficient computational resources are available. Experiments demonstrate that the ESP method allows evolved virtual creatures to reach new levels of behavioral complexity in the co-evolution of morphology and control, approximately doubling the previous state of the art.