TY - JOUR
T1 - Skill acquisition through program-level imitation in a real-time domain
AU - Wood, M A
AU - Bryson, J J
N1 - ID number: ISI:000245109300003
PY - 2007
Y1 - 2007
N2 - This paper presents an imitation learning system capable of learning tasks in a complex dynamic real-time environment. In this paper, we argue that social learning should be thought of as a special case of general skill learning, and that the biases it presents to the skill learning problem radically simplify learning for species with sufficient innate predisposition to harness this power. We decompose skill learning into four subproblems, then show how a modification of Roy's CELL system can address all these problems simultaneously. Our system is demonstrated working in the domain of a real-time virtual-reality game, Unreal Tournament.
AB - This paper presents an imitation learning system capable of learning tasks in a complex dynamic real-time environment. In this paper, we argue that social learning should be thought of as a special case of general skill learning, and that the biases it presents to the skill learning problem radically simplify learning for species with sufficient innate predisposition to harness this power. We decompose skill learning into four subproblems, then show how a modification of Roy's CELL system can address all these problems simultaneously. Our system is demonstrated working in the domain of a real-time virtual-reality game, Unreal Tournament.
UR - http://dx.doi.org/10.1109/tsmcb.2006.886948
U2 - 10.1109/tsmcb.2006.886948
DO - 10.1109/tsmcb.2006.886948
M3 - Article
SN - 1083-4419
VL - 37
SP - 272
EP - 285
JO - IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics
JF - IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics
IS - 2
ER -