In our Markovian model of the learner's environment, the environment is described by a Markov chain on a finite state space [NI with transition matrix P = (pij) ...

This paper initiates study of such models under weaker Markovian assumptions on the observations, In the special case where the sequence of hypotheses ...

Abstract: A model of learning that expands on the Valiant model is introduced. The point of departure from the Valiant model is that the learner is placed ...

In previous work, observations were assumed to be stochastically independent. This paper initiates study of such models under weaker Markovian assumptions on ...

A model of learning that expands on the Valiant model is introduced. The point of departure from the Valiant model is that the learner is placed in a ...

David J. Aldous, Umesh V. Vazirani: A Markovian Extension of Valiant's Learning Model (Extended Abstract). FOCS 1990: 392-396. manage site settings.

On the Expressiveness of Temporal Logic Programming. M. Baudinet. Pages 157-180 ; A Markovian Extension of Valiant′s Learning Model. D. Aldous, U. Vazirani.

Abstract— We extend Valiant's probably approximately correct. (PAC) model of learning to Markov decision processes (MDPs).

Valiant's probably approximately correct (PAC) model of learning to Markov decision processes (MDPs) is extended and uniform sample complexity results for ...

A Markovian extension of Valiant's learning model, 31st Annual Symposium on Foundations of Computer Science, 1990. F. Carrat, A. Carrat, and . Flahault ...