Evolving soccer keepaway players through task decomposition

doi:10.1007/s10994-005-0460-9

Evolving soccer keepaway players through task decomposition

2005-05-01

62

OA

AI

DOI：10.1007/s10994-005-0460-9

Original

Original request for help

Save

Abstract

En 中文

Complex control tasks can often be solved by decomposing them into hierarchies of manageable subtasks. Such decompositions require designers to decide how much human knowledge should be used to help learn the resulting components. On one hand, encoding human knowledge requires manual effort and may incorrectly constrain the learner's hypothesis space or guide it away from the best solutions. On the other hand, it may make teaming easier and enable the learner to tackle more complex tasks. This article examines the impact of this trade-off in tasks of varying difficulty. A space laid out by two dimensions is explored: (1) how much human assistance is given and (2) how difficult the task is. In particular, the neuroevolution teaming algorithm is enhanced with three different methods for teaming the components that result from a task decomposition. The first method, coevolution, is mostly unassisted by human knowledge. The second method, layered teaming, is highly assisted. The third method, concurrent layered teaming, is a novel combination of the first two that attempts to exploit human knowledge while retaining some of coevolution's flexibility. Detailed empirical results are presented comparing and contrasting these three approaches on two versions of a complex task, namely robot soccer keepaway, that differ in difficulty of teaming. These results confirm that, given a suitable task decomposition, neuroevolution can master difficult tasks. Furthermore, they demonstrate that the appropriate level of human assistance depends critically on the difficulty of the problem.

Keywords:

coevolution

neural networks

genetic algorithms

Robot soccer

Evolving soccer keepaway players through task decomposition

Abstract

Journal

Organization