Domains featuring this topic
Explore the domains where this topic appears.
Learning Relational Rules from Rewards
Humans perceive the world in terms of objects and relations between them. In fact, for any given pair of objects, there is a myriad of relations that apply to them. How does the cognitive system learn which relations are useful to characterize the task at hand? And how can it use these representations to build a relational policy to interact effectively with the environment? In this paper we propose that this problem can be understood through the lens of a sub-field of symbolic machine learning called relational reinforcement learning (RRL). To demonstrate the potential of our approach, we build a simple model of relational policy learning based on a function approximator developed in RRL. We trained and tested our model in three Atari games that required to consider an increasingly number of potential relations: Breakout, Pong and Demon Attack. In each game, our model was able to select adequate relational representations and build a relational policy incrementally. We discuss the relationship between our model with models of relational and analogical reasoning, as well as its limitations and future directions of research.
NeurotechEU Summit
Our first NeurotechEU Summit will be fully digital and will take place on November 22th from 09:00 to 17:00 (CET). The final programme can be downloaded here. Hosted by the Karolinska Institutet, the summit will provide you an overview of our actions and achievements from the last year and introduce the priorities for the next year. You will also have the opportunity to attend the finals of the 3 minute thesis competition (3MT) organized by the Synapses Student Society, the student charter of NeurotechEU. Good luck to all the finalists: Lynn Le, Robin Noordhof, Adriana Gea González, Juan Carranza Valencia, Lea van Husen, Guoming (Tony) Man, Lilly Pitshaporn Leelaarporn, Cemre Su, Kaya Keleş, Ramazan Tarık Türksoy, Cristiana Tisca, Sara Bandiera, Irina Maria Vlad, Iulia Vadan, Borbála László, and David Papp! Don’t miss our keynote lecture, success stories and interactive discussions with Ms Vanessa Debiais Sainton (Head of Higher Education Unit, European Commission), Prof. Staffan Holmin (Karolinska Institutet), Dr Mohsen Kaboli (BMW Group, member of the NeurotechEU Associates Advisory Committee), and Prof. Peter Hagoort (Max Planck Institute for Psycholinguistics, Donders Institute). Would you like to use this opportunity to network? Please join our informal breakout sessions on Wonder.me at 11:40 CET. You will be able to move from one discussion group to another within 3 sessions: NeurotechEU ecosystem - The Associates Advisory Committee: Synergies in cross-sectoral initiatives Education next: Trans-European education and the European Universities Initiatives - Lessons learned thus far. Equality, diversity and inclusion at NeurotechEU: removing access barriers to education and developing a working, learning, and social environment where everyone is respected and valued. You can register for this free event at www.crowdcast.io/e/neurotecheu-summit
Physics of Behavior: Now that we can track (most) everything, what can we do with the data?
We will organize the workshop around one question: “Now that we can track (most) everything, what can we do with the data?” Given the recent dramatic advances in technology, we now have behavioral data sets with orders of magnitude more accuracy, dimensionality, diversity, and size than we had even a few years ago. That being said, there is still little agreement as to what theoretical frameworks can inform our understanding of these data sets and suggest new experiments we can perform. We hope that after this workshop we’ll see a variety of new ideas and perhaps gain some inspiration. We have invited eight speakers, each studying different systems, scales, and topics, to provide 10 minute presentations focused on the above question, with another 10 minutes set aside for questions/discussions (moderated by the two of us). Although we naturally expect speakers to include aspects of their own work, we have encouraged all of them to think broadly and provocatively. We are also hoping to organize some breakout sessions after the talks so that we can have some more expanded discussions about topics arising during the meeting.