Jörg Hähner

Predictive Load Balancing in Cloud Computing Environments Based on Ensemble Forecasting

2016

Cloud Computing allows the on-demand usage of computing resources in a pay-as-you-use manner. One major problem for Cloud providers is the trade-off between the huge amount of energy consumption resulting from the non optimal utilisation …

Toward curious learning classifier systems

2017 · Proceedings of the Genetic and Evolutionary Computation Conference Companion

This paper proposes a novel approach to enhance the rather reactive knowledge generation process in Learning Classifier Systems (LCS) toward a more proactive means. We describe how concepts from the domain of Active Learning can …

D2.2 Uncertainty-Aware Sensor Fusion in Sensor Networks

2021

Uncertainty assignment for measurement values is a common process for single sensors, but this procedure grows in complexity for sensor networks. Often measured values are processed further in such networks and uncertainty must be evaluated …

Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments

2021 · Algorithms

State-of-the-art Deep Reinforcement Learning Algorithms such as DQN and DDPG use the concept of a replay buffer called Experience Replay. The default usage contains only the experiences that have been gathered over the runtime. We …

Analysing the Influence of Reorder Strategies for Cartesian Genetic Programming

2024 · arXiv (Cornell University)

Cartesian Genetic Programming (CGP) suffers from a specific limitation: Positional bias, a phenomenon in which mostly genes at the start of the genome contribute to a program output, while genes at the end rarely do. …