Online reinforcement learning for human-robot interactive learning
Coping with the variability of human feedback during interactive learning through ensemble reinforcement learning
Research Bundles
"Research bundles" give you a space in the AI on-demand platform where you can collect and publish the outputs of a small research project in a compact way. A research bundle collects in a single place all the assets (code, data, tutorials, examples, ...) produced by your project and published on the AI on-demand platform. Of course, you can also put links to assets published elsewhere, like Github or Zenodo.
Optimal Alerting
This project looks at a novel method that can help intelligent systems alert users who are multitasking.
Pluralistic Recommendation in News
Perform unbiased recommendation for news in the European domain. To achieve it, build a political leaning classifier on a EU-News Dataset
Polarization with the Friedkin-Johnsen model over a dynamic social network
This project investigates the impact of dynamic social graphs on polarization with the Friedkin-Johnsen opinion dynamic model. The model can reproduce also special users in the network with extreme or neutral opinions and not willing to change their minds...
Proactive communication in social robots
The goal of this micro-project is to develop a cognitive architecture able to generate proactive communicative behaviors during human-robot interactions.
Reasoning on Contextual Hierarchies via Answer Set Programming with Algebraic Measures
We generalize the CKR framework for contextual knowledge repositories with more complex preference relations and realize its computation using the asprin framework.
SciNoBo: A Collaborative AI Assistant in Science Communication
An AI system, that identifies statements in news media (Health,Climate), providing scientific evidence and simplifying the language of the scientific discourse.
Social AI gossiping
We envision a human-AI ecosystem in which AI-enabled devices act as proxies of humans and try to learn collectively a model.
Socially Aware Interactions
A Humane-AI-Net micro-project that aims to address the limitations of scripted dialogue training systems.
Temporal and biological factors of our vulnerability to disinformation
Analysing the exogenous factors impacting our judgement of and response to information