Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this pape...
A connectionist model for robust reasoning, CONSYDERR, is proposed to account for some common reasoning patterns found in commonsense reasoning and to remedy the brittleness probl...
The SINAI1 research group presents some results obtained after performing a brief analysis to the query logs from The European Library2 (TEL). The objective of the LogCLEF task is ...
This paper describes a stochastic programming model that was developed for asset liability management of a Finnish pension insurance company. In many respects the model resembles t...
Petri Hilli, Matti Koivu, Teemu Pennanen, Antero R...
This study uses cognitive psychological experiments to elucidate human temporal co-creation with environments or other people. Time series analyses of alternate tapping with const...