We propose a probabilistic, generative account of configural learning phenomena in classical conditioning. Configural learning experiments probe how animals discriminate and gener...
Aaron C. Courville, Nathaniel D. Daw, David S. Tou...
We consider approximate policy evaluation for finite state and action Markov decision processes (MDP) in the off-policy learning context and with the simulation-based least square...
Buchberger’s Gr¨obner basis theory plays a fundamental role in symbolic computation. The resulting algorithms essentially carry out several S-polynomial reductions. In his PhD ...
We examine the conditions under which we can keep simplicity or categoricity after adding a Skolem function to the theory. AMS classification: 03C45 , 03C50
The present study aims at insights into the nature of incremental learning in the context of Gold’s model of identification in the limit. With a focus on natural requirements s...