Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

AB Arrieta, N Díaz-Rodríguez, J Del Ser, A Bennetot… - Information fusion, 2020 - Elsevier
In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if
harnessed appropriately, may deliver the best of expectations over many application sectors …

[HTML][HTML] Autonomous agents modelling other agents: A comprehensive survey and open problems

SV Albrecht, P Stone - Artificial Intelligence, 2018 - Elsevier
Much research in artificial intelligence is concerned with the development of autonomous
agents that can interact effectively with other agents. An important aspect of such agents is …

Model-free opponent shaping

C Lu, T Willi, CAS De Witt… - … Conference on Machine …, 2022 - proceedings.mlr.press
In general-sum games the interaction of self-interested learning agents commonly leads to
collectively worst-case outcomes, such as defect-defect in the iterated prisoner's dilemma …

A survey of real-time strategy game AI research and competition in StarCraft

S Ontanón, G Synnaeve, A Uriarte… - … Intelligence and AI …, 2013 - ieeexplore.ieee.org
This paper presents an overview of the existing work on AI for real-time strategy (RTS)
games. Specifically, we focus on the work around the game StarCraft, which has emerged in …

In the blink of an eye: leveraging blink-induced suppression for imperceptible position and orientation redirection in virtual reality

E Langbehn, F Steinicke, M Lappe, GF Welch… - ACM Transactions on …, 2018 - dl.acm.org
Immersive computer-generated environments (aka virtual reality, VR) are limited by the
physical space around them, eg, enabling natural walking in VR is only possible by …

COLA: consistent learning with opponent-learning awareness

T Willi, AH Letcher, J Treutlein… - … on Machine Learning, 2022 - proceedings.mlr.press
Learning in general-sum games is unstable and frequently leads to socially undesirable
(Pareto-dominated) outcomes. To mitigate this, Learning with Opponent-Learning …

A survey of opponent modeling in adversarial domains

S Nashed, S Zilberstein - Journal of Artificial Intelligence Research, 2022 - jair.org
Opponent modeling is the ability to use prior knowledge and observations in order to predict
the behavior of an opponent. This survey presents a comprehensive overview of existing …

Greybox XAI: A Neural-Symbolic learning framework to produce interpretable predictions for image classification

A Bennetot, G Franchi, J Del Ser, R Chatila… - Knowledge-Based …, 2022 - Elsevier
Abstract Although Deep Neural Networks (DNNs) have great generalization and prediction
capabilities, their functioning does not allow a detailed explanation of their behavior …

[PDF][PDF] Identifying patterns in combat that are predictive of success in MOBA games.

P Yang, BE Harrison, DL Roberts - FDG, 2014 - ciigar.csc.ncsu.edu
ABSTRACT Multiplayer Online Battle Arena (MOBA) games rely primarily on combat to
determine the ultimate outcome of the game. Combat in these types of games is highly …

Artificial intelligence and virtual worlds–toward human-level AI agents

VM Petrović - IEEE Access, 2018 - ieeexplore.ieee.org
Artificial Intelligence (AI) has a long tradition as a scientific field, with tremendous
achievements accomplished in the decades behind us. At the same time, in the last few …