Multi−Task Evolutionary Shaping Without Pre−Specified Representations

Abstract

Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, researchers have pre-specified a separate representation for shaping and value functions in multi-task settings. However, no work has made precise what distinguishes these representations, or what makes a good representation for either function. This paper shows two alternative methods by which an evolutionary algorithm can find a shaping function in multi-task RL without pre-specifying a separate representation. The second method, which uses an indirect fitness measure, is demonstrated to achieve similar performance to the first against a significantly lower computational cost. In addition, we define a formal categorisation of representations that makes precise what makes a good representation for shaping and value functions. We validate the categorisation with an evolutionary feature selection method and show that this method chooses the representations that our definitions predict are suitable.