University
of Hertfordshire
Adaptive
Systems Research Group
| Department of Computer Science University of Hertfordshire Hatfield AL10 9AB United Kingdom |
|
I'm a PhD student at the University of Hertfordshire since December 2007. I work with the Adaptive Systems Group in the department of Computer Sciences and the department of Philosophy. My principal supervisor is Daniel Polani and my second supervisor is Daniel Hutto.
My main research interest is in modeling and simulating aspects of social interaction with the help of information theory. I am especially interested in the transfer of information between agents and how such a system can evolve from a simple model to display complex behavior.
This borders on several areas of philosophy, mainly the theory of mind and the theories regarding social interaction. Here we try to investigate how exactly those two fields are connected, and how and if the results of one field can be applied to the other. This also involves the clarification of several terms which are commonly used by both disciplines.
A further interest of mine are the models behind game mechanics. I am interested in how AIs can be adapted to different challenges, and how that influences the design of games itself.
| (2009) Christoph Salge and Daniel Polani: Information Driven Organization of Visual Receptive Fields, Advances in Complex Systems (ACS), vol. 12, issue 03, pages 311-326 (BibTeX) |
||
| Abstract: By using information theory to reduce the state space of sensor arrays, such as receptive fields, for AI decision making we offer an adaptive algorithm without classical biases of hand coded approaches. This paper presents a way to build an acyclic directed graph to organize the sensor inputs of a visual receptive field. The Information Distance Metric is used to repeatedly select two sensors, which contain the most information about each other. Those are then encoded to a single variable, of equal alphabet size, with a deterministic mapping function that aims to create maximal entropy while maintaining a low information distance to the original sensors. The resulting tree determines which sensors are fused to reduce the input data while maintaining a maximum of information. The structure adapts to different environments of input images by encoding groups of preferred line structures or creating a higher resolution for areas with simulated movement. These effects are created without prior assumptions about the sensor statistics or the spatial configuration of the receptive field, and are cheap to compute since only pair-wise informational comparison of sensors is used. | ||
| (2008) Salge, C., Lipski, C.,Mahlmann, T. and Mathiak, B.: Using Genetically Optimized AIs to improve Gameplaying Fun for Strategical Games, in Proc. of SIGGRAPH Sandbox 2008, Los Angeles, pages 7 -14 (PDF) (BibTeX) |
||
| Abstract: Fun in computer games depends on many factors. While some factors like uniqueness and humor can only be measured by human subjects, in a strategical game, the rule system is an important and measurable factor. Classics like chess and GO have a millennia-old story of success, based on clever rule design. They only have a few rules, are relatively easy to understand, but still they have myriads of possibilities. Testing the deepness of a rule-set is very hard, especially for a rule system as complex as in a classic strategic computer game. It is necessary, though, to ensure prolonged gaming fun. In our approach, we use artificial intelligence (AI) to simulate hours of beta-testing the given rules, tweaking the rules to provide more game-playing fun and deepness. To avoid making the AI a mirror of its programmer’s gaming preferences, we not only evolved the AI with a genetic algorithm, but also used three fundamentally different AI paradigms to find boring loopholes, inefficient game mechanisms and, last but not least, complex erroneous behavior. | ||
(2008) Salge, C. and Polani, D. Information Driven Organization of Visual Receptive Fields, in Proc. of GWAL 2008, Leipzig (PDF)
|
||
| Abstract: This paper presents a way to build a treelike network structure to organise the sensor inputs of a visual receptive field. The Information Distance Metric is used to repeatedly select two sensors, which contain the most information about each other. Those are then encoded to a single variable of equal capacity with a mapping function that tries to create maximal entropy while maintaining a low information distance to the original sensors. The resulting tree determines which sensors are fused to reduce the input data while maintaining maximum information. The structure adapts to different environments of input images, by encoding groups of preferred line structures or creating a higher resolution of areas with simulated movement. These effects are created without prior assumption of the environment or the spatial configuration of the receptive field and are cheap to compute, since only pairwise informational comparison of sensors is used. | ||
| (2009) Christoph Salge and Daniel Polani: Information Theoretic Incentives for Social Interaction, Technical Report 495, University of Hertfordshire, Hatfield (PDF) |
||
| Abstract: A first step towards social interaction is to observe other agents and their actions. The concept of "Relevant Information" is used to argue, from an information theoretic perspective, why it would be beneficial to observe other agents, and why observing their actions should be relevant to me, even if their actions are not. A simple grid world model illustrates those points, for a simple information gathering task, and shows how to utilise this information to increase an agent's performance. | ||