In real life, learning is greatly speeded-up by the intervention of a teacher who gives examples, or shows, how to perform a certain task. In all this abstract, we let apart structural simpli cations of the problem by the designer which to not deal explicitely with learning. The intervention of the teacher can be realized in di erent ways: verbal explanation, demonstration, guidance, shaping th...

Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their generality, good convergence properties, and possible biological relevance. In this paper, we introduce an online temporal difference based actor-critic algorithm which is proved to converge to a neighborhood of a local m...

Propositional argumentation systems are based on assumption based reasoning and used for computing arguments which support a given hypotheses Assumption based reasoning is closely related to hypothetical default theories or inference through theory formation The latter approach known as the Theorist frame work has well known relations to abduction and default reasoning In this paper proposition...

For intelligent robots to accomplish tasks in an unstructured environment, the adaptive critic algorithm has been shown to provide useful approximations or even optimal control policies to non-linear systems. The purpose of this paper is to explore the use of new learning control methods defined as Creative Learning or Creative Control that goes beyond the adaptive critic method for unstructure...

We consider the estimation of the policy gradient in partially observable Markov decision processes (POMDP) with a special class of structured policies that are finite-state controllers. We show that the gradient estimation can be done in the Actor-Critic framework, by making the critic compute a “value” function that does not depend on the states of POMDP. This function is the conditional mean...