Sciweavers

Share
GECCO
2010
Springer

Multi-task evolutionary shaping without pre-specified representations

9 years 5 months ago
Multi-task evolutionary shaping without pre-specified representations
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 t...
Matthijs Snel, Shimon Whiteson
Added 02 Sep 2010
Updated 02 Sep 2010
Type Conference
Year 2010
Where GECCO
Authors Matthijs Snel, Shimon Whiteson
Comments (0)
books