Robert Müller

Jonas Nüßlein, Steffen Illium, Robert Müller et al.

Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little expert data as possible. In this paper we present an algorithm that imitates the higher-level strategy of the expert rather than just imitating the expert on action level, which we hypothesize requires less expert data and makes training more stable. As a prior, we assume that the higher-level strategy is to reach an unknown target state area, which we hypothesize is a valid prior for many domains in Reinforcement Learning. The target state area is unknown, but since the expert has demonstrated how to reach it, the agent tries to reach states similar to the expert. Building on the idea of Temporal Coherence, our algorithm trains a neural network to predict whether two states are similar, in the sense that they may occur close in time. During inference, the agent compares its current state with expert states from a Case Base for similarity. The results show that our approach can still learn a near-optimal policy in settings with very little expert data, where algorithms that try to imitate the expert at the action level can no longer do so.

Robert Müller, Clemens Müller

We introduce \textsc{Cattle Trade, a multi-agent benchmark for evaluating large language models (LLMs) as agents in strategic reasoning under imperfect information, adversarial interaction, and resource constraints. The benchmark combines auctions, hidden-offer trade challenges (TCs), bargaining, bluffing, opponent modeling, and resource allocation within a single long-horizon game lasting 50--60 turns. Unlike prior agent benchmarks that test these abilities in isolation, \textsc{Cattle Trade} evaluates whether agents integrate them across a competitive, multi-agent economic game with conflicting incentives. The benchmark logs every bid, TC offer, counteroffer, and card selection, enabling behavioural analysis beyond final scores or win rates. We evaluate seven cost-efficient language models and three deterministic code agents across 242 games. Strategic coherence, in particular spending efficiency, resource discipline, and phase-adaptive bidding, is associated with rank more strongly than spending volume or any single subskill. Two heuristic code agents outperform most tested LLMs, and behavioural traces surface recurring LLM failure modes including overbidding, self-bidding, bankrupt TC initiation, and weak opponent-state adaptation. Evaluating agentic competence requires benchmarks that test the joint deployment of multiple capabilities in multi-agent environments with conflicting incentives, uncertainty, and economic dynamics.

Robert Müller, Hasan Turalic, Thomy Phan et al.

In the realm of Multi-Agent Reinforcement Learning (MARL), prevailing approaches exhibit shortcomings in aligning with human learning, robustness, and scalability. Addressing this, we introduce ClusterComm, a fully decentralized MARL framework where agents communicate discretely without a central control unit. ClusterComm utilizes Mini-Batch-K-Means clustering on the last hidden layer's activations of an agent's policy network, translating them into discrete messages. This approach outperforms no communication and competes favorably with unbounded, continuous communication and hence poses a simple yet effective strategy for enhancing collaborative task-solving in MARL.

Robert Müller

This paper demonstrates that Semantic Context (SC), leveraging descriptive tool information, is a foundational component for robust tool orchestration. Our contributions are threefold. First, we provide a theoretical foundation using contextual bandits, introducing SC-LinUCB and proving it achieves lower regret and adapts favourably in dynamic action spaces. Second, we provide parallel empirical validation with Large Language Models, showing that SC is critical for successful in-context learning in both static (efficient learning) and non-stationary (robust adaptation) settings. Third, we propose the FiReAct pipeline, and demonstrate on a benchmark with over 10,000 tools that SC-based retrieval enables an LLM to effectively orchestrate over a large action space. These findings provide a comprehensive guide to building more sample-efficient, adaptive, and scalable orchestration agents.

Tobias Rohe, Barbara Böhm, Michael Kölle et al.

Drones have revolutionized various domains, including agriculture. Recent advances in deep learning have propelled among other things object detection in computer vision. This study utilized YOLO, a real-time object detector, to identify and count coconut palm trees in Ghanaian farm drone footage. The farm presented has lost track of its trees due to different planting phases. While manual counting would be very tedious and error-prone, accurately determining the number of trees is crucial for efficient planning and management of agricultural processes, especially for optimizing yields and predicting production. We assessed YOLO for palm detection within a semi-automated framework, evaluated accuracy augmentations, and pondered its potential for farmers. Data was captured in September 2022 via drones. To optimize YOLO with scarce data, synthetic images were created for model training and validation. The YOLOv7 model, pretrained on the COCO dataset (excluding coconut palms), was adapted using tailored data. Trees from footage were repositioned on synthetic images, with testing on distinct authentic images. In our experiments, we adjusted hyperparameters, improving YOLO's mean average precision (mAP). We also tested various altitudes to determine the best drone height. From an initial mAP@.5 of $0.65$, we achieved 0.88, highlighting the value of synthetic images in agricultural scenarios.

Robert Müller, Aldo Pacchiano

We study meta-learning in Markov Decision Processes (MDP) with linear transition models in the undiscounted episodic setting. Under a task sharedness metric based on model proximity we study task families characterized by a distribution over models specified by a bias term and a variance component. We then propose BUC-MatrixRL, a version of the UC-Matrix RL algorithm, and show it can meaningfully leverage a set of sampled training tasks to quickly solve a test task sampled from the same task distribution by learning an estimator of the bias parameter of the task distribution. The analysis leverages and extends results in the learning to learn linear regression and linear bandit setting to the more general case of MDP's with linear transition models. We prove that compared to learning the tasks in isolation, BUC-Matrix RL provides significant improvements in the transfer regret for high bias low variance task distributions.

Andreas Sedlmeier, Michael Kölle, Robert Müller et al.

Model-based Deep Reinforcement Learning (RL) assumes the availability of a model of an environment's underlying transition dynamics. This model can be used to predict future effects of an agent's possible actions. When no such model is available, it is possible to learn an approximation of the real environment, e.g. by using generative neural networks, sometimes also called World Models. As most real-world environments are stochastic in nature and the transition dynamics are oftentimes multimodal, it is important to use a modelling technique that is able to reflect this multimodal uncertainty. In order to safely deploy such learning systems in the real world, especially in an industrial context, it is paramount to consider these uncertainties. In this work, we analyze existing and propose new metrics for the detection and quantification of multimodal uncertainty in RL based World Models. The correct modelling & detection of uncertain future states lays the foundation for handling critical situations in a safe way, which is a prerequisite for deploying RL systems in real-world settings.

Steffen Illium, Robert Müller, Andreas Sedlmeier et al.

In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The idea here is to reduce model over-fitting to the feature distribution of a small under-descriptive training dataset. We try to evaluate such data augmentation techniques to gather insights in the performance boost they provide for several convolutional neural networks on mel-spectrogram representations of audio data. We show the impact of data augmentation on the binary classification task of surgical mask detection in samples of human voice (ComParE Challenge 2020). Also we consider four varying architectures to account for augmentation robustness. Results show that most of the baselines given by ComParE are outperformed.