Abstract. Perfectly rational decision-makers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here we employ an axiomat...
Engineers have long used control systems utilizing models and feedback loops to control realworld systems. Limitations of model-based control led to a generation of intelligent co...
Kazuhiko Kawamura, Stephen M. Gordon, Palis Ratana...
A coevolutionary competitive learning environment for two antagonistic agents is presented. The agents are controlled by a new kind of computational network based on a compartment...
Gul Muhammad Khan, Julian Francis Miller, David M....
We present an extension of the Dynamics Based Control (DBC) paradigm to environment models based on Predictive State Representations (PSRs). We show an approximate greedy version ...
Ariel Adam, Zinovi Rabinovich, Jeffrey S. Rosensch...
Abstract. We present a model of motor learning based on a combination of Operational Space Control and Optimal Control. Anticipatory processes are used both in the learning of the ...