Acting (WP5)

Partners

UNIROMA1, CNR, UCC, UPF, CNRS, VUB, UArtois, CVUT, TU Delft, DFKI, EPFL, FBK , RWTH AACHEN, CINI, UNIPI, UNIBAS, UPV

See partner page for details on participating organisations.

People

Giuseppe De Giacomo (UNIROMA1), WP leader.

Task 5.1: Extended and multi-facet models of the world dynamics and tasks (Giuseppe De Giacomo)

Task 5.2: Integrating data-based methods with model-based methods in deciding and learning how to act (Hector Geffner)

Task 5.3: Learning for reasoners and planners, and reasoners and planners for learning (Malte Helmert)

Task 5.4: Monitoring and controlling to make actions AI trustworthy in the real world (Paolo Traverso)

Task 5.5: Synergies Industry, Challenges, Roadmap concerning autonomous actions in AI systems (Andreas Herzig)

Task 5.6: Fostering the AI scientific community on the theme of deciding and learning how to act (Gerhard Lakemeyer)

About WP5

This research theme focuses on the fundamental question: how does an AI agent decide and learn on how to act?

The present theme aims at empowering the agent with the ability of deliberating autonomously (i.e., without human intervention) how to act in the world. That is reasoning on the effects of its actions, learning from past experiences (or simulation of experiences), as well as monitoring the actual outcome of its actions, learning possibly unexpected outcomes, and again reasoning and learning how to deal with such new outcomes.

Crucially, empowering an AI agent with the ability to self-deliberate its own behavior and act autonomously, carries significant risks and therefore we must be able to balance such power with safety. This means that the autonomy of the agent must be guarded by human guided specifications and oversight, to make it verifiable and comprehensible in human terms and ultimately trustworthy.

If you are interested in contributing to this work-package, please subscribe to the TAILOR WP5 google group.

Contact: Giuseppe De Giacomo (degiacomo@diag.uniroma1.it)

News related to WP5