Digital zero-sum games are a challenging domain for artificial intelligence techniques. In such games, human players often resort to strategies, i.e., memorized sequences of low-level actions that guide their behavior. In this research we model this way ...

Existing machine-learning work has shown that algorithms can benefit from curricula---learning first on simple examples before moving to more difficult examples. While most existing work on curriculum learning focuses on developing automatic methods to ...

In recent years, work has been done to develop the theory of General Reinforcement Learning (GRL). However, there are no examples demonstrating the known results regarding generalised discounting. We have added to the GRL simulation platform (AIXIjs) ...

Nature provides us with a multitude of examples that show how swarms of simple agents are much richer in their abilities than a single individual. This insight is a main principle that swarm robotics tries to exploit. In the last years, large swarms of ...

Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be extended to ...

Complex tasks for heterogeneous data sources, such as finding and linking named entities in text documents or detecting objects in images, often require multiple steps to be solved in a processing pipeline. In most of the cases, there exist numerous, ...

We introduce a probabilistic graphical model of ranked preferences for social choice based on a restricted version of a kth-order Markov tree. The system is similar to Plackett's model, and is based on the intuition that, in some domains, an agent's ...

Robust training of deep neural networks requires a large amount of data. However gathering and labeling this data can be expensive and determining which distribution of features are needed for training is not a trivial problem. This is compounded when ...

Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. ...