This paper describes the adaption and application of an algorithm called Feudal Reinforcement Learning to a complex gridworld navigation problem. The algorithm proved to be not ea...
In visual processing the ability to deal with missing and noisy information is crucial. Occlusions and unreliable feature detectors often lead to situations where little or no dir...
We present a new connectionist planning method TML90 . By interaction with an unknown environment, a world model is progressively constructed using gradient descent. For deriving ...
Previous work (M.I. Sereno, 1989; cf. M.E. Sereno, 1987) showed that a feedforward network with area V1-like input-layer units and a Hebb rule can develop area MT-like second laye...
A new class of data structures called "bumptrees" is described. These structures are useful for efficiently implementing a number of neural network related operations. A...