Alle Publikationen
- <<
- <
- 1
2018
-
(2018): Fair is foul, and foul is fair. Experimental evolutionary studies of mismatch. In: Journal of Bioeconomics 20 (1), S. 153-157. DOI: 10.1007/s10818-017-9266-7
Abstract: We describe two types of experimental evolution studies of 'mismatch' that are relevant to economics. 'Evolutionary mismatch' is the concept that an organism can be importantly 'out of sync' with its environment. In such cases, an organism may choose an option that is inferior to a feasible alternative. Mainstream and behavioral economics do not address the notion of evolutionary mismatch. We argue for an empirical program on mismatch utilizing the methodology of experimental evolution. (PsycINFO Database Record (c) 2018 APA, all rights reserved)
2017
-
(2017): An Evolutionary Transfer Reinforcement Learning Framework for Multiagent Systems. In: IEEE Transactions on Evolutionary Computation 21 (4), S. 601-615. DOI: 10.1109/TEVC.2017.2664665
Abstract: In this paper, we present an evolutionary transfer reinforcement learning framework (eTL) for developing intelligent agents capable of adapting to the dynamic environment of multiagent systems (MASs). Specifically, we take inspiration from Darwin's theory of natural selection and Universal Darwinism as the principal driving forces that govern the evolutionary knowledge transfer process. The essential backbone of our proposed eTL comprises several meme-inspired evolutionary mechanisms, namely meme representation, meme expression, meme assimilation, meme internal evolution, and meme external evolution. Our proposed approach constructs social selection mechanisms that are modeled after the principles of human learning to identify appropriate interacting partners. eTL also models the intrinsic parallelism of natural evolution and errors that are introduced due to the physiological limits of the agents' ability to perceive differences, so as to generate "growth" and "variation" of knowledge that agents have of the world, thus exhibiting higher adaptivity capabilities on solving complex problems. To verify the efficacy of the proposed paradigm, comprehensive investigations of the proposed eTL against existing state-of-the-art TL methods in MAS, are conducted on the "minefield navigation tasks" platform and the "Unreal Tournament 2004" first person shooter computer game, in which homogeneous and heterogeneous learning machines are considered.
2014
-
(2014): An auction behavior-based robotic architecture for service robotics. In: Intelligent Service Robotics 7 (3), S. 157-174. DOI: 10.1007/s11370-013-0141-7
DOI: https://doi.org/10.1007/s11370-013-0141-7 Abstract: Service robots have the potential of improving the quality of life and assist with people’s daily activities. Such robots must be capable of operating over long periods of time, performing multiple tasks, and scheduling them appropriately for execution. In addition, service robots must be capable of dealing with tasks whose goals may be in conflict with each other and would need to determine, dynamically, which task to pursue in such a case. Adding to the complexity of the problem is the fact that some task requests may have time constraints—deadlines by which the task has to be completed. Given the dynamic nature of the environment, the robots must make decisions on what tasks to pursue in situations where there could be incomplete or missing information. The robots should also be capable of accepting requests for new tasks or services at runtime, while possibly working on another task. In order to achieve these requirements, this paper presents the Auction Behavior-Based Robotic Architecture that brings the following contributions: (1) it uses an auction mechanism to determine the relevance of a task to run at any given time, (2) it handles multiple user requests while dealing with potentially critical time constraints and incomplete information, (3) it enables long-term robot operation and (4) it allows for dynamic assignment of new tasks. The proposed system is validated on a physical robotic platform, the Segway RMP® and in simulation. (PsycINFO Database Record (c) 2016 APA, all rights reserved)
- <<
- <
- 1