Hideaki Takeda's Publication

• A. Ueno and H. Takeda: Cooperation of Categorical and Behavioral Learning in a Practical Solution to the Abstraction Problem, New Generation Computing, Vol. 19, pp. 257–282 (2001). (Paper)

  Real robots should be able to adapt autonomously tovarious environments in order to go on executing their tasks without breaking down. They achieve this by learning how to abstract only useful information from a huge amount of information in the environment while executing their tasks. This paper proposes a new architecture which performs categorical learning and behavioral learning in parallel with task execution. We call the architecture Situation Transition Network System (STNS). In categorical learning, it makes a flexible state representation and modifies it according to the results of behaviors. Behavioral learning is reinforcement learning on the state representation. Simulation results have shown that this architecture is able to learn efficiently and adapt to unexpected changes of the environment autonomously.