In this work, we present the results of a thorough analysis of the BN-robot's dynamics. We analysed the trajectories followed by the BN-robot in the space of the BN states. We found that the best performing BNs show the capability of maintaining previous learned behaviours (robustness), while adapting to new tasks to perform (evolvability). This property seems also to be positively correlated with a measure of the complexity of the BN.
Robustness, evolvability and complexity in Boolean network robots / A. Roli; S. Benedettini; M. Birattari; C. Pinciroli; R. Serra; M. Villani. - ELETTRONICO. - (2011), pp. 117-118. (Intervento presentato al convegno ECCS2011 - European Conference on Complex Systems tenutosi a Vienna nel 12-16 September 2011).
Robustness, evolvability and complexity in Boolean network robots
ROLI, ANDREA;BENEDETTINI, STEFANO;
2011
Abstract
In this work, we present the results of a thorough analysis of the BN-robot's dynamics. We analysed the trajectories followed by the BN-robot in the space of the BN states. We found that the best performing BNs show the capability of maintaining previous learned behaviours (robustness), while adapting to new tasks to perform (evolvability). This property seems also to be positively correlated with a measure of the complexity of the BN.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.