Hideaki Takeda's Publication
- A. Ueno, H. Takeda and T. Nishida: Learning of the Way of
Abstraction in Real Robots, in Proceedings of 1999 IEEE International
Conference on Systems, Man, and Cybernetics (SMC 99) (CD-ROM), Vol. 1,
pp. II746–II751 (1999).
Real robots should be able to adapt flexibly to various
environments. The main problem is how to abstract useful information from a
huge amount of information in the environment. This is called the frame
problem. This paper proposes a new architecture which can learn how to
perform abstraction while executing the task. We call the architecture
Situation Transition Network System (STNS). By this architecture, a robot can
acquire a necessary and sufficient symbol system for the current task and
environment. Furthermore, this symbol system is flexible enough to adapt to
changes of the environment. STNS performs cognitive learning and behavior
learning parallelly while executing the task. In cognitive learning, it
extracts situations and maintains them dynamically in the continuous state
space on the basis of rewards from the environment. A situation can be
regarded as an empirically obtained symbol. In behavior learning, it
constructs an MDP (Markov Decision Problem) model of the environment on the
abstracted situation representation. This model is used for planning of
behavior. The validity of STNS is shown in computer simulations.
Hideaki Takeda (National Institute of Informatics)