Modelling shared attention through relational reinforcement learning

Shared attention is a type of communication very important among human beings. It is sometimes reserved for the more complex form of communication being constituted by a sequence of four steps: mutual gaze, gaze following, imperative pointing and declarative pointing. Some approaches have been proposed in Human-Robot Interaction area to solve part of shared attention process, that is, the most of works proposed try to solve the first two steps. Models based on temporal difference, neural networks, probabilistic and reinforcement learning are methods used in several works. In this article, we are presenting a robotic architecture that provides a robot or agent, the capacity of learning mutual gaze, gaze following and declarative pointing using a robotic head interacting with a caregiver. Three learning methods have been incorporated to this architecture and a comparison of their performance has been done to find the most adequate to be used in real experiment. The learning capabilities of this architecture have been analyzed by observing the robot interacting with the human in a controlled environment. The experimental results show that the robotic head is able to produce appropriate behavior and to learn from sociable interaction.

Non-Dominated Sorting Genetic Algorithm Based on Reinforcement Learning to Optimization of Broad-Band Reflector Antennas Satellite

This paper aims to provide an improved NSGA-II (Non-Dominated Sorting Genetic Algorithm-version II) which incorporates a parameter-free self-tuning approach by reinforcement learning technique, called Non-Dominated Sorting Genetic Algorithm Based on Reinforcement Learning (NSGA-RL). The proposed method is particularly compared with the classical NSGA-II when applied to a satellite coverage problem. Furthermore, not only the optimization results are compared with results obtained by other multiobjective optimization methods, but also guarantee the advantage of no time-spending and complex parameter tuning.

Cocaine effects on mouse incentive-learning and human addiction are linked to alpha 2 subunit-containing GABA(A) receptors

Because GABA(A) receptors containing alpha 2 subunits are highly represented in areas of the brain, such as nucleus accumbens (NAcc), frontal cortex, and amygdala, regions intimately involved in signaling motivation and reward, we hypothesized that manipulations of this receptor subtype would influence processing of rewards. Voltage-clamp recordings from NAcc medium spiny neurons of mice with alpha 2 gene deletion showed reduced synaptic GABA(A) receptor-mediated responses. Behaviorally, the deletion abolished cocaine`s ability to potentiate behaviors conditioned to rewards (conditioned reinforcement), and to support behavioral sensitization. In mice with a point mutation in the benzodiazepine binding pocket of alpha 2-GABA(A) receptors (alpha 2H101R), GABAergic neurotransmission in medium spiny neurons was identical to that of WT (i.e., the mutation was silent), but importantly, receptor function was now facilitated by the atypical benzodiazepine Ro 15-4513 (ethyl 8-amido-5,6-dihydro-5-methyl-6-oxo-4H-imidazo [1,5-a] [1,4] benzodiazepine-3-carboxylate). In alpha 2H101R, but not WT mice, Ro 15-4513 administered directly into the NAcc-stimulated locomotor activity, and when given systemically and repeatedly, induced behavioral sensitization. These data indicate that activation of alpha 2-GABA(A) receptors (most likely in NAcc) is both necessary and sufficient for behavioral sensitization. Consistent with a role of these receptors in addiction, we found specific markers and haplotypes of the GABRA2 gene to be associated with human cocaine addiction.