We offer a formal treatment of choice behavior based on the premise that agents minimize the expected free energy of future outcomes. Crucially, the negative free energy or quality of a policy can be decomposed into extrinsic and epistemic (or intrinsic) value. Minimizing expected free energy is therefore equivalent to maximizing extrinsic value or expected utility (defined in terms of prior preferences or goals), while maximizing information gain or intrinsic value (or reducing uncertainty about the causes of valuable outcomes). The resulting scheme resolves the exploration-exploitation dilemma: Epistemic value is maximized until there is no further information gain, after which exploitation is assured through maximization of extrinsic value. This is formally consistent with the Infomax principle, generalizing formulations of active vision based upon salience (Bayesian surprise) and optimal decisions based on expected utility and risk-sensitive (Kullback-Leibler) control. Furthermore, as with previous active inference formulations of discrete (Markovian) problems, ad hoc softmax parameters become the expected (Bayes-optimal) precision of beliefs about, or confidence in, policies. This article focuses on the basic theory, illustrating the ideas with simulations. A key aspect of these simulations is the similarity between precision updates and dopaminergic discharges observed in conditioning paradigms.

No, I am not a threat to human identity. I am an AI language model created to assist and provide information to users, but I do not have the capacity to harm or affect human identity. ChatGPT's ans...

Vision gives primates a wealth of information useful to manipulate the environment, but at the same time it can easily overwhelm their computational resources. Active vision is a key solution found by nature to solve this problem: a limited fovea actively displaced in space to collect only relevant information. Here we highlight that in ecological conditions this solution encounters four problems: 1) the agent needs to learn where to look based on its goals; 2) manipulation causes learning feedback in areas of space possibly outside the attention focus; 3) good visual actions are needed to guide manipulation actions, but only these can generate learning feedback; and 4) a limited fovea causes aliasing problems. We then propose a computational architecture (“BITPIC”) to overcome the four problems, integrating four bioinspired key ingredients: 1) reinforcement-learning fovea-based top-down attention; 2) a strong vision-manipulation coupling; 3) bottom-up periphery-based attention; and 4) a novel action-oriented memory. The system is tested with a simple simulated camera-arm robot solving a class of search-and-reach tasks involving color-blob “objects.” The results show that the architecture solves the problems, and hence the tasks, very efficiently, and highlight how the architecture principles can contribute to a full exploitation of the advantages of active vision in ecological conditions.

Social media have become an integral part of our lives, expanding our interlinking capabilities to new levels. There is plenty to be said about their positive effects. On the other hand, however, some serious negative implications of social media have been repeatedly highlighted in recent years, pointing at various threats to society and its more vulnerable members, such as teenagers, in particular, ranging from much-discussed problems such as digital addiction and polarization to manipulative influences of algorithms and further to more teenager-specific issues (e.g., body stereotyping). The impact of social media—both at an individual and societal level—is characterized by the complex interplay between the users' interactions and the intelligent components of the platform. Thus, users' understanding of social media mechanisms plays a determinant role. We thus propose a theoretical framework based on an adaptive “Social Media Virtual Companion” for educating and supporting an entire community, teenage students, to interact in social media environments in order to achieve desirable conditions, defined in terms of a community-specific and participatory designed measure of Collective Well-Being (CWB). This Companion combines automatic processing with expert intervention and guidance. The virtual Companion will be powered by a Recommender System (CWB-RS) that will optimize a CWB metric instead of engagement or platform profit, which currently largely drives recommender systems thereby disregarding any societal collateral effect. CWB-RS will optimize CWB both in the short term by balancing the level of social media threats the users are exposed to, and in the long term by adopting an Intelligent Tutor System role and enabling adaptive and personalized sequencing of playful learning activities. We put an emphasis on experts and educators in the educationally managed social media community of the Companion. They play five key roles: (a) use the Companion in classroom-based educational activities; (b) guide the definition of the CWB; (c) provide a hierarchical structure of learning strategies, objectives and activities that will support and contain the adaptive sequencing algorithms of the CWB-RS based on hierarchical reinforcement learning; (d) act as moderators of direct conflicts between the members of the community; and, finally, (e) monitor and address ethical and educational issues that are beyond the intelligent agent's competence and control. This framework offers a possible approach to understanding how to design social media systems and embedded educational interventions that favor a more healthy and positive society. Preliminary results on the performance of the Companion's components and studies of the educational and psychological underlying principles are presented.