11 Papers from DoC accepted at AAAI and AAMAS in 2024

AAAI is to promote research in AI and foster scientific exchange and AAMAS is the largest conference in the area of agents and multiagent systems

Eleven papers coauthored by members of the Department of Computing have been accepted at the 38th Annual AAAI Conference on Artificial
Intelligence (AAAI 2024) and the 23rd International Conference on
Autonomous Agents and Multi-Agent Systems (AAMAS 2024).

The purpose of AAAI is to promote research in AI and foster scientific
exchange between researchers, practitioners, scientists, students, and
engineers.

AAMAS is the largest and most influential conference in the area of
agents and multiagent systems.


Papers accepted at AAAI:

- F. Leofante and N. Potyka; Promoting Counterfactual Robustness through
Diversity.

- M. Flageat, B. Lim and A. Cully; Beyond Expected Return: Accounting
for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms

- M. Dombrowski, H. Reynaud, J. Müller, M. Baugh and B. Kainz;
Trade-offs in Fine-tuned Diffusion Models Between Accuracy and
Interpretability.

- Zhang, Williams, and Toni; Targeted Activation Penalties help CNNs
ignore spurious signals.

- Ulbricht,  Potyka, Rapberger and Toni; Non-flat ABA is an Instance of
Bipolar Argumentation.

- A. Hussain and F. Belardinelli; Stability of Multi-Agent Learning in
Competitive Networks: Delaying the Onset of Chaos.


Papers accepted at AAMAS:

- J. Jiang, A. Rago, F. Leofante and F. Toni; Recourse under Model
Multiplicity via Argumentative Ensembling.

- A. Goodall and F. Belardinelli; Leveraging Approximate Model-based
Shielding for Probabilistic Safety Guarantees in Continuous Environments.

- F. Ward, M. MacDermott, F. Belardinelli, F. Toni and T. Everitt; The
Reasons that Agents Act: Intention and Instrumental Goals.

- F. Belardinelli, W. Jamroga, M. Mittelmann and A. Murano; Verification
of Stochastic Multi-Agent Systems with Forgetful Strategies.

- A. Hussain, D. Leonte, F. Belardinelli and G. Piliouras; On the
Stability of Learning in Network Games with Many Players.