In order to have a robotic system able to effectively learn by imitation, and not merely reproduce the movements of a human teacher, the system should have the capabilities of deeply understanding the perceived actions to be imitated. This paper deals with the development of cognitive architecture

The cognitive dimensions framework is a broad-brush evaluation technique for interactive devices and for non-interactive notations. It sets out a small vocabulary of terms designed to capture the cognitively-relevant aspects of structure, and shows how they can be traded off against each other

A framework for skill acquisition is proposed that includes two major stages in the development of a cognitive skill: a declarative stage in which facts about the skill domain are interpreted and a procedural stage in which the domain knowledge is directly embodied in procedures for performing

Abstract — This paper presents a definition and framework for a novel type of adaptive data network: the cognitive network. In a cognitive network, the collection of elements that make up the network observes network conditions and then, using prior knowledge gained from previous interactions

that a major reason for the ineffectiveness of problem solving as a learning device, is that the cognitive processes required by the two activities overlap insufficiently, and that conventional problem solving in the form of means-ends analysis requires a relatively large amount of cognitive processing

Spanning seven orders of magnitude: a challenge for

…Truth [is] being involved in an eternal conversation about things that matter, conducted with passion and discipline…truth is not in the conclusions so much as in the process of conversation itself…if you want to be in truth you must be in conversation. Parker Palmer

torques. Overall, we show that options enable temporally abstract knowledge and action to be included in the reinforcement learning framework in a natural and general way. In particular, we show that options may be used interchangeably with primitive actions in planning methods such as dynamic

in their behavior. The framework of Markov games allows us to widen this view to include multiple adaptive agents with interacting or competing goals. This paper considers a step in this direction in which exactly two agents with diametrically opposed goals share an environment. It describes a Q-learning

We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised framework that incorporates labeled and unlabeled data in a general-purpose learner. Some transductive graph learning