Half-baked, Ad-hoc and Noisy: Minimal Simulations for Evolutionary Robotics

This paper puts forward a theoretical framework and formal language for understanding how simple , fast simulations can be used to artiicially evolve controllers for real robots. It begins by putting forward a general set of equations that describe the way in which an agent-environment system changes over time, and analyses what it means for an agent to exhibit a particular behaviour within such a system. A minimally suf-cient set of conditions are then formally established under which a controller that reliably displays a particular behaviour in one system will continue to display the same behaviour when transplanted into another system, and the special case of behavioural transference from simulation into reality is evaluated within the context of this theoretical framework. From this, techniques are derived for ensuring that controllers which are reliably t within a simulation will transfer into reality, and two sets of experiments are brieey described in which controllers that evolved in extremely minimal simulations were able to perform non-trivial and robust behaviours when down-loaded onto real robots.