ALVIS is a reinforcement-based connectionist architecture that learns associative maps in continuous multidimensional environ(cid:173) ments. The discovered locations of positive and negative rein(cid:173) forcements are recorded in "do be" and "don't be" subnetworks, respectively. The outputs of the subnetworks relevant to the cur(cid:173) rent goal are combined and compared with the current location to produce an error vector. This vector is backpropagated through a motor-perceptual mapping network. AL VIS is demonstrated with a simulated robot posed a target-seeking task.

ALVIS is a reinforcement-based connectionist architecture that learns associative maps in continuous multidimensional environments. The discovered locations of positive and negative reinforcements are recorded in "do be" and "don't be" subnetworks, respectively. The outputs of the subnetworks relevant to the current goal are combined and compared with the current location to produce an error vector. This vector is backpropagated through a motor-perceptual mapping network.

ALVIS is a reinforcement-based connectionist architecture that learns associative maps in continuous multidimensional environments. Thediscovered locations of positive and negative reinforcements arerecorded in "do be" and "don't be" subnetworks, respectively. The outputs of the subnetworks relevant to the current goalare combined and compared with the current location to produce an error vector. This vector is backpropagated through a motor-perceptual mapping network.

ALVIS is a reinforcement-based connectionist architecture that learns associative maps in continuous multidimensional environments. The discovered locations of positive and negative reinforcements are recorded in "do be" and "don't be" subnetworks, respectively. The outputs of the subnetworks relevant to the current goal are combined and compared with the current location to produce an error vector. This vector is backpropagated through a motor-perceptual mapping network.