Learned mutation strategies in genetic programming for evolution and adaptation of simulated snakebot

In this work we propose an approach of incorporating learned mutation strategies (LMS) in genetic programming (GP) employed for evolution and adaptation of locomotion gaits of simulated snake-like robot (Snakebot). In our approach the LMS are implemented via learned probabilistic context-sensitive grammar (LPCSG). The LPCSG is derived from the originally defined context-free grammar, which usually expresses the syntax of genetic programs in canonical GP. Applying LMS implies that the probabilities of applying each of particular production rules in LPCGS during the mutation depend on the context. These probabilities are learned from the aggregated reward values obtained from the parsed syntax of the evolved best-of-generation Snakebots. Empirically obtained results verify that LMS contributes to the improvement of computational effort of both (i) the evolution of the fastest possible locomotion gaits for various fitness conditions and (ii) the adaptation of these locomotion gaits to challenging environment and degraded mechanical abilities of Snakebot. In all of the cases considered in this study, the locomotion gaits, evolved and adapted employing GP with LMS feature higher velocity and are obtained faster than with canonical GP.