Abstract | ||
---|---|---|
ABSTRACTThe MAP-Elites quality-diversity algorithm has been successful in robotics because it can create a behaviorally diverse set of solutions that later can be used for adaptation, for instance to unanticipated damages. In MAP-Elites, the choice of the behaviour space is essential for adaptation, the recovery of performance in unseen environments, since it defines the diversity of the solutions. Current practice is to hand-code a set of behavioural features, however, given the large space of possible behaviour-performance maps, the designer does not know a priori which behavioural features maximise a map's adaptation potential. We introduce a new meta-evolution algorithm that discovers those behavioural features that maximise future adaptations. The proposed method applies Covariance Matrix Adaptation Evolution Strategy to evolve a population of behaviour-performance maps to maximise a meta-fitness function that rewards adaptation. The method stores solutions found by MAP-Elites in a database which allows to rapidly construct new behaviour-performance maps on-the-fly. To evaluate this system, we study the gait of the RHex robot as it adapts to a range of damages sustained on its legs. When compared to MAP-Elites with user-defined behaviour spaces, we demonstrate that the meta-evolution system learns high-performing gaits with or without damages injected to the robot. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1145/3377930.3390181 | Genetic and Evolutionary Computation Conference |
Keywords | DocType | Citations |
quality-diversity algorithms, behavioural diversity, meta-learning, evolutionary robotics, damage recovery | Conference | 2 |
PageRank | References | Authors |
0.37 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bossens David M. | 1 | 3 | 2.08 |
Jean-Baptiste Mouret | 2 | 1041 | 58.13 |
Danesh Tarapore | 3 | 169 | 10.76 |