Game Theory
game theory
Ing. Mgr. Jaroslav Hlinka, Ph.D.
Postdoctoral / Junior Scientist position in Complex Networks and Information Theory A Postdoc or Junior Scientist position is available to join the Complex Networks and Brain Dynamics group for the project: “Network modelling of complex systems: from correlation graphs to information hypergraphs“ funded by the Czech Science Foundation. The project involves developing, optimizing and applying techniques for modelling complex dynamical systems beyond the currently available methods of complex network analysis and game theory. The project is carried out in collaboration with the Artificial Intelligence Center of the Czech Technical University. Conditions: • Contract is of 18 months duration (with the possibility of follow-up tenure-track application). • Starting date: position is available immediately. • Applications will be reviewed on a rolling basis with a first cut-off point on 30. 9. 2022. • This is a full-time fixed term contract appointment. Part time contract negotiable. • Monthly gross salary: 42 000 - 48 000 CZK based on qualifications and experience. Cost Of Living Comparison • Bonuses depending on performance and travel funding for conferences and research stays. • Contribution for reallocation costs for succesful applicant coming from abroad: 10 000 CZK plus 10 000 CZK for family (spouse and/or children). • No teaching duties
N/A
This project is about developing reinforcement-learning based AI systems that directly interact with some segment of society. The applications include matching and other allocation problems. The research will be performed at the interface between reinforcement learning, social choice theory, Bayesian inference, mechanism design, differential privacy and algorithmic fairness. The research will have both a theoretical and practical component, which will include some experiments with humans. However, a good theoretical background in probability, machine learning or game theory is necessary for all students. The positions are available from January 2024. The PhD lasts for 4 years and includes a small teaching component.
N/A
The project is about developing reinforcement-learning based AI systems that directly interact with some segment of society. The applications include matching and other allocation problems. The research will be performed at the interface between reinforcement learning, social choice theory, Bayesian inference, mechanism design, differential privacy and algorithmic fairness. The research will have both a theoretical and practical component, which will include some experiments with humans.
A Game Theoretical Framework for Quantifying Causes in Neural Networks
Which nodes in a brain network causally influence one another, and how do such interactions utilize the underlying structural connectivity? One of the fundamental goals of neuroscience is to pinpoint such causal relations. Conventionally, these relationships are established by manipulating a node while tracking changes in another node. A causal role is then assigned to the first node if this intervention led to a significant change in the state of the tracked node. In this presentation, I use a series of intuitive thought experiments to demonstrate the methodological shortcomings of the current ‘causation via manipulation’ framework. Namely, a node might causally influence another node, but how much and through which mechanistic interactions? Therefore, establishing a causal relationship, however reliable, does not provide the proper causal understanding of the system, because there often exists a wide range of causal influences that require to be adequately decomposed. To do so, I introduce a game-theoretical framework called Multi-perturbation Shapley value Analysis (MSA). Then, I present our work in which we employed MSA on an Echo State Network (ESN), quantified how much its nodes were influencing each other, and compared these measures with the underlying synaptic strength. We found that: 1. Even though the network itself was sparse, every node could causally influence other nodes. In this case, a mere elucidation of causal relationships did not provide any useful information. 2. Additionally, the full knowledge of the structural connectome did not provide a complete causal picture of the system either, since nodes frequently influenced each other indirectly, that is, via other intermediate nodes. Our results show that just elucidating causal contributions in complex networks such as the brain is not sufficient to draw mechanistic conclusions. Moreover, quantifying causal interactions requires a systematic and extensive manipulation framework. The framework put forward here benefits from employing neural network models, and in turn, provides explainability for them.
On climate change, multi-agent systems and the behaviour of networked control
Multi-agent reinforcement learning (MARL) has recently shown great promise as an approach to networked system control. Arguably, one of the most difficult and important tasks for which large scale networked system control is applicable is common-pool resource (CPR) management. Crucial CPRs include arable land, fresh water, wetlands, wildlife, fish stock, forests and the atmosphere, of which proper management is related to some of society’s greatest challenges such as food security, inequality and climate change. This talk will consist of three parts. In the first, we will briefly look at climate change and how it poses a significant threat to life on our planet. In the second, we will consider the potential of multi-agent systems for climate change mitigation and adaptation. And finally, in the third, we will discuss recent research from InstaDeep into better understanding the behaviour of networked MARL systems used for CPR management. More specifically, we will see how the tools from empirical game-theoretic analysis may be harnessed to analyse the differences in networked MARL systems. The results give new insights into the consequences associated with certain design choices and provide an additional dimension of comparison between systems beyond efficiency, robustness, scalability and mean control performance.