9 citations · 25 across the 10 of their papers we have counts for
12 papers
Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits
Yannik Mahlau, Maximilian Schier, Christoph Reinders +3
Inverse design of photonic integrated circuits (PICs) has traditionally relied on gradientbased optimization. However, this approach is prone to end up in local minima, which resul…
HydraMix: Multi-Image Feature Mixing for Small Data Image Classification
Christoph Reinders, Frederik Schubert, Bodo Rosenhahn
Training deep neural networks requires datasets with a large number of annotated examples. The collection and annotation of these datasets is not only extremely expensive but also…
A flexible framework for large-scale FDTD simulations: open-source inverse design for 3D nanostructures
Yannik Mahlau, Frederik Schubert, Konrad Bethmann +5
We introduce an efficient open-source python package for the inverse design of three-dimensional photonic nanostructures using the Finite-Difference Time-Domain (FDTD) method. Leve…
Quantized Inverse Design for Photonic Integrated Circuits
Frederik Schubert, Yannik Mahlau, Konrad Bethmann +5
The inverse design of photonic integrated circuits (PICs) presents distinctive computational challenges, including their large memory requirements. Advancements in the two-photon p…
Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
Yannik Mahlau, Frederik Schubert, Bodo Rosenhahn
The combination of self-play and planning has achieved great successes in sequential games, for instance in Chess and Go. However, adapting algorithms such as AlphaZero to simultan…
POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning
Frederik Schubert, Carolin Benjamins, Sebastian Döhler +2
The goal of Unsupervised Reinforcement Learning (URL) is to find a reward-agnostic prior policy on a task domain, such that the sample-efficiency on supervised downstream tasks is…
ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing
Christoph Reinders, Frederik Schubert, Bodo Rosenhahn
Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmenta…
Contextualize Me -- The Case for Context in Reinforcement Learning
Carolin Benjamins, Theresa Eimer, Frederik Schubert +6
While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes.…
CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning
Carolin Benjamins, Theresa Eimer, Frederik Schubert +4
While Reinforcement Learning has made great strides towards solving ever more complicated tasks, many algorithms are still brittle to even slight changes in their environment. This…
World-GAN: a Generative Model for Minecraft Worlds
Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generat…
Automatic Risk Adaptation in Distributional Reinforcement Learning
Frederik Schubert, Theresa Eimer, Bodo Rosenhahn +1
The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its enviro…
TOAD-GAN: Coherent Style Level Generation from a Single Example
Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
In this work, we present TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates to…