Papers have already shown that CNNs are capable of classifying clouds into their meteorological types. This thesis aims to use these classifications to produce short-term… Read More »Weather Forecast by Determining Cloud Types for Home Automation
We had our 6th AI-FM workshop, bringing together the Postdocs, PhD- and research students of Prof. Nils Jansen from both RUB and Radboud University in… Read More »6th AI-FM Workshop
This work investigates post-hoc calibration as a means of providing reinforcement learning (RL) agents with lightweight uncertainty estimation that can shape decision-making behavior. Calibration techniques… Read More »Uncertainty-Aware Perception for Reinforcement Learning Agents
This thesis investigates feature space reduction and state space discretization in reinforcement learning for vision-based navigation tasks. The focus lies on comparing the performance of… Read More »On Feature Space Reduction and State Space Discretization: A Pipeline for Vision-Based Reinforcement Learning
This September, two members of our lab participated in the European Workshop on Reinforcement Learning (EWRL), one of the leading international gatherings for the RL… Read More »Posters at the EWRL 2025 — All Good Things Come in Threes
Reinforcement learning researchers face integration challenges when selecting tools to create experiments. The existing tooling for reinforcement learning is vast but poorly integrated across frameworks.… Read More »Omnigym – A versatile Framework for Reinforcement Learning Research