Narrow Results

The basal ganglia system has been proposed as a possible neural substrate for action selection in the vertebrate brain. We describe a robotic implementation of a model of the basal ganglia and demonstrate the capacity of this system to generate adaptive switching between several acts when embedded in a robot that has to "survive" in a laboratory environment. A comparison between this brain-inspired selection mechanism and classical "winner-takes-all" selection highlights some adaptive properties specific to the model, such as avoidance of dithering and energy-saving. These properties derive, in part, from the capacity of simulated basal ganglia-thalamo-cortical loops to generate appropriate "behavioral persistence".

The mechanisms of decision-making and action selection are generally thought to be under the control of parallel cortico-subcortical loops connecting back to distinct areas of cortex through the basal ganglia and processing motor, cognitive and limbic modalities of decision-making. We have used these properties to develop and extend a connectionist model at a spiking neuron level based on a previous rate model approach. This model is demonstrated on decision-making tasks that have been studied in primates and the electrophysiology interpreted to show that the decision is made in two steps. To model this, we have used two parallel loops, each of which performs decision-making based on interactions between positive and negative feedback pathways. This model is able to perform two-level decision-making as in primates. We show here that, before learning, synaptic noise is sufficient to drive the decision-making process and that, after learning, the decision is based on the choice that has proven most likely to be rewarded. The model is then submitted to lesion tests, reversal learning and extinction protocols. We show that, under these conditions, it behaves in a consistent manner and provides predictions in accordance with observed experimental data.

This paper proposes a novel action selection method based on quantum computation and reinforcement learning (RL). Inspired by the advantages of quantum computation, the state/action in a RL system is represented with quantum superposition state. The probability of action eigenvalue is denoted by probability amplitude, which is updated according to rewards. And the action selection is carried out by observing quantum state according to collapse postulate of quantum measurement. The results of simulated experiments show that quantum computation can be effectively used to action selection and decision making through speeding up learning. This method also makes a good tradeoff between exploration and exploitation for RL using probability characteristics of quantum theory.

The main motivation for this work is to investigate the advantages provided by machine consciousness, while in the control of software agents. In order to pursue this goal, we developed a cognitive architecture, with different levels of machine consciousness, targeting the control of artificial creatures. As a standard guideline, we applied cognitive neuroscience concepts to incrementally develop the cognitive architecture, following the evolutionary steps taken by the animal brain. The triune brain theory proposed by MacLean, together with Arrabale's "ConsScale", serve as roadmaps to achieve each developmental stage, while iCub — a humanoid robot and its simulator — serve as a platform for the experiments. A completely codelet-based system "Core" has been implemented, serving the whole architecture.

This article argues that conscious attention exists not so much for selecting an immediate action as for using the current task to focus specialized learning for the action-selection mechanism(s) and predictive models on tasks and environmental contingencies likely to affect the conscious agent. It is perfectly possible to build this sort of a system into machine intelligence, but it would not be strictly necessary unless the intelligence needs to learn and is resource-bounded with respect to the rate of learning versus the rate of relevant environmental change. Support for this theory is drawn from scientific research and AI simulations. Consequences are discussed with respect to self-consciousness and ethical obligations to and for AI.