Quick post to share another joint work with a brilliant master student, Pasquale Roseti, that co-authored with me and Franco Zambonelli his very first scientific publication at AAMAS 2023 :)
The warmest congratulations to Pasquale, bravo!
In brief, the paper proposes a multi-agent protocol to collaboratively discover (= learn) the causal structure relating variables of interest (e.g. sensors and actuators) in a distributed network. The study is motivated by the fact that learning not only correlations amongst variables (as classical statistical ML does) but actual causal relations (as per level 2 of Pearl’s ladder of causation) is crucial to let agents proficiently understand situations and plan accordingly how to achieve their goals in unknown environments, also favouring explainability of decisions taken by AI.
The key results achieved are:
- learning accuracy is always better with multi-agent learning than with single-agent learning
- learning performance is always better in the multi-agent case, too, to an extent increasing as the causal network size and complexity increases (e.g. number of edges and indirect causal paths length)
The core idea of the approach is to leverage any existing causal discovery algorithm locally to each agent, then refine the locally learnt model by coordinating interventions with other agents sharing the environment, even when no overlap exists amongst the set of known variables.
The paper has been accepted as an extended abstract, hence stay tuned for an update of a full paper version coming soon :) Feel free to contact me for a pre-print or any further inquiry :)
Peace.
