@article{PollatosMoenkemoellerGroppeetal.2023,
  author    = {Pollatos, Olga and M{\"o}nkem{\"o}ller, Karla and Groppe, Karoline and Elsner, Birgit},
  title     = {Interoceptive accuracy is associated with benefits in decision making in children},
  series = {Frontiers in psychology},
  volume    = {13},
  journal   = {Frontiers in psychology},
  publisher = {Frontiers Research Foundation},
  address   = {Lausanne},
  issn      = {1664-1078},
  doi       = {10.3389/fpsyg.2022.1070037},
  pages     = {13},
  year      = {2023},
  abstract  = {Introduction: Decision making results not only from logical analyses, but seems to be further guided by the ability to perceive somatic information (interoceptive accuracy). Relations between interoceptive accuracy and decision making have been exclusively studied in adults and with regard to complex, uncertain situations (as measured by the Iowa Gambling Task, IGT). Methods: In the present study, 1454 children (6-11 years) were examined at two time points (approximately 1 year apart) using an IGT as well as a delay-of-gratification task for sweets-items and toy-items. Interoceptive accuracy was measured using a child-adapted version of the Heartbeat Perception Task. Results: The present results revealed that children with higher, as compared to lower, interoceptive accuracy showed more advantageous choices in the IGT and delayed more sweets-items, but not toy-items, in a delay-of-gratification task at time point 2 but not at time point 1. However, no longitudinal relation between interoceptive accuracy and decision making 1 year later could be shown. Discussion: Results indicate that interoceptive accuracy relates to decision-making abilities in situations of varying complexity already in middle childhood, and that this link might consolidate across the examined 1-year period. Furthermore, the association of interoceptive accuracy and the delay of sweets-items might have implications for the regulation of body weight at a later age.},
  language  = {en}
}
@phdthesis{Tan2023,
  author    = {Tan, Jing},
  title     = {Multi-Agent Reinforcement Learning for Interactive Decision-Making},
  doi       = {10.25932/publishup-60700},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-607000},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 135},
  year      = {2023},
  abstract  = {Distributed decision-making studies the choices made among a group of interactive and self-interested agents. Specifically, this thesis is concerned with the optimal sequence of choices an agent makes as it tries to maximize its achievement on one or multiple objectives in the dynamic environment. The optimization of distributed decision-making is important in many real-life applications, e.g., resource allocation (of products, energy, bandwidth, computing power, etc.) and robotics (heterogeneous agent cooperation on games or tasks), in various fields such as vehicular network, Internet of Things, smart grid, etc. This thesis proposes three multi-agent reinforcement learning algorithms combined with game-theoretic tools to study strategic interaction between decision makers, using resource allocation in vehicular network as an example. Specifically, the thesis designs an interaction mechanism based on second-price auction, incentivizes the agents to maximize multiple short-term and long-term, individual and system objectives, and simulates a dynamic environment with realistic mobility data to evaluate algorithm performance and study agent behavior. Theoretical results show that the mechanism has Nash equilibria, is a maximization of social welfare and Pareto optimal allocation of resources in a stationary environment. Empirical results show that in the dynamic environment, our proposed learning algorithms outperform state-of-the-art algorithms in single and multi-objective optimization, and demonstrate very good generalization property in significantly different environments. Specifically, with the long-term multi-objective learning algorithm, we demonstrate that by considering the long-term impact of decisions, as well as by incentivizing the agents with a system fairness reward, the agents achieve better results in both individual and system objectives, even when their objectives are private, randomized, and changing over time. Moreover, the agents show competitive behavior to maximize individual payoff when resource is scarce, and cooperative behavior in achieving a system objective when resource is abundant; they also learn the rules of the game, without prior knowledge, to overcome disadvantages in initial parameters (e.g., a lower budget). To address practicality concerns, the thesis also provides several computational performance improvement methods, and tests the algorithm in a single-board computer. Results show the feasibility of online training and inference in milliseconds. There are many potential future topics following this work. 1) The interaction mechanism can be modified into a double-auction, eliminating the auctioneer, resembling a completely distributed, ad hoc network; 2) the objectives are assumed to be independent in this thesis, there may be a more realistic assumption regarding correlation between objectives, such as a hierarchy of objectives; 3) current work limits information-sharing between agents, the setup befits applications with privacy requirements or sparse signaling; by allowing more information-sharing between the agents, the algorithms can be modified for more cooperative scenarios such as robotics.},
  language  = {en}
}