Searcharxiv⌕ Search

arXiv subjects

Tobias Glasmachers

Publications and source records attributed to Tobias Glasmachers.

At least 19 recordsLinked to original sources
arXiv2026

Macro-Action Topological Navigation under Noisy Localization using Reinforcement Learning

Navigating large, photorealistic 3D apartments from raw pixels is widely considered infeasible for plain reinforcement learning. We build an agent that does it anyway, estimating its own pose from the camera alone. The agent has to reach several target objects in sequence, and their positions change between episodes, so it must explore to find them. It builds on our earlier object-centric topological controller, which still read the agent's true pose and its object detections from the simulator. Here we replace that true pose with an onboard, object-centric estimate. For each object we keep a bank of ORB features that, when the object is seen again, yield a rough pose measurement, which a minimal Extended Kalman Filter (EKF) fuses with a motion model. As on a real robot, the executed motions are noisy. The estimate drifts, but the agent and the nearby objects drift together, so a locally consistent pose is enough to follow each short edge and then home in visually on the target, which lets us replace full SLAM with a much smaller model, closer to how biological navigation appears to work. In the photorealistic Habitat simulator, the agent reaches its target objects from vision alone, with a pose that only needs to be locally consistent.

cs.LG↗
arXiv2026

Applicability of memorization indicators for early spotting of overfitting while recalibrating sEMG-decoders on low sample sizes

Deep learning models for surface electromyography (sEMG) can benefit substantially from subject-specific (re-)calibration, since no sufficiently large and diverse datasets are available to train fully generic decoders. However, for user acceptance, the number of repetitions that can realistically be collected during calibration is severely limited, which increases the risk of overfitting and, in extreme cases, can even degrade performance compared to the uncalibrated model. Classical overfitting indicators such as validation performance and regularization with early stopping are difficult to apply in this low-sample regime, as they require additional held-out data that is rarely available in practical calibration scenarios. In this work, we investigate a recently proposed class of memorization indicators based solely on the activation statistics of rectified linear units (ReLU) in deep neural networks, which can be computed directly from training data without any extra validation set. We conduct a transferlearning experiment on a benchmark sEMG dataset, where a convolutional neural network is first pre-trained on multiple subjects and subsequently fine-tuned on individual users using only a small number of repetitions. During calibration, we monitor both decoding performance and the activation behaviour of the last hidden layer. Our results provide first evidence that decreases in test accuracy during fine-tuning are ac companied by characteristic changes in activation rates, indicating that activation-based memorization indicators are a promising tool for early spotting of unsuccessful learning in low-sample sEMG calibration settings.

cs.LG↗
arXiv2026

Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control

Reinforcement learning (RL) is still rarely applied in industrial control, partly due to the difficulty of training reliable agents for real-world conditions. This work investigates how evolution strategies can support RL in such settings by introducing a continuous-control adaptation of an industrial sorting benchmark. The CMA-ES algorithm is used to generate high-quality demonstrations that warm-start RL agents. Results show that CMA-ES-guided initialization significantly improves stability and performance. Furthermore, the demonstration trajectories generated with the CMA-ES provide a strong oracle reference performance level, which is of interest in its own right. The study delivers a focused proof of concept for hybrid evolutionary-RL approaches and a basis for future, more complex industrial applications.

cs.NE↗
arXiv2025

Benchmarking that Matters: Rethinking Benchmarking for Practical Impact

Benchmarking has driven scientific progress in Evolutionary Computation, yet current practices fall short of real-world needs. Widely used synthetic suites such as BBOB and CEC isolate algorithmic phenomena but poorly reflect the structure, constraints, and information limitations of continuous and mixed-integer optimization problems in practice. This disconnect leads to the misuse of benchmarking suites for competitions, automated algorithm selection, and industrial decision-making, despite these suites being designed for different purposes. We identify key gaps in current benchmarking practices and tooling, including limited availability of real-world-inspired problems, missing high-level features, and challenges in multi-objective and noisy settings. We propose a vision centered on curated real-world-inspired benchmarks, practitioner-accessible feature spaces and community-maintained performance databases. Real progress requires coordinated effort: A living benchmarking ecosystem that evolves with real-world insights and supports both scientific understanding and industrial use.

cs.NE↗
arXiv2025

Balancing Specialization and Centralization: A Multi-Agent Reinforcement Learning Benchmark for Sequential Industrial Control

Autonomous control of multi-stage industrial processes requires both local specialization and global coordination. Reinforcement learning (RL) offers a promising approach, but its industrial adoption remains limited due to challenges such as reward design, modularity, and action space management. Many academic benchmarks differ markedly from industrial control problems, limiting their transferability to real-world applications. This study introduces an enhanced industry-inspired benchmark environment that combines tasks from two existing benchmarks, SortingEnv and ContainerGym, into a sequential recycling scenario with sorting and pressing operations. We evaluate two control strategies: a modular architecture with specialized agents and a monolithic agent governing the full system, while also analyzing the impact of action masking. Our experiments show that without action masking, agents struggle to learn effective policies, with the modular architecture performing better. When action masking is applied, both architectures improve substantially, and the performance gap narrows considerably. These results highlight the decisive role of action space constraints and suggest that the advantages of specialization diminish as action complexity is reduced. The proposed benchmark thus provides a valuable testbed for exploring practical and robust multi-agent RL solutions in industrial automation, while contributing to the ongoing debate on centralization versus specialization.

cs.LG↗
arXiv2025

Cumulative Learning Rate Adaptation: Revisiting Path-Based Schedules for SGD and Adam

The learning rate is a crucial hyperparameter in deep learning, with its ideal value depending on the problem and potentially changing during training. In this paper, we investigate the practical utility of adaptive learning rate mechanisms that adjust step sizes dynamically in response to the loss landscape. We revisit a cumulative path-based adaptation scheme proposed in 2017, which adjusts the learning rate based on the discrepancy between the observed path length, computed as a time-discounted sum of normalized gradient steps, and the expected length of a random walk. While the original approach offers a compelling intuition, we show that its adaptation mechanism for Adam is conceptually inconsistent due to the optimizer's internal preconditioning. We propose a corrected variant that better reflects Adam's update dynamics. To assess the practical value of online learning rate adaptation, we benchmark SGD and Adam, with and without cumulative adaptation, and compare them to a recent alternative method. Our results aim to clarify when and why such adaptive strategies offer practical benefits.

cs.LG↗
arXiv2025

Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments

Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges such as sample inefficiency and unstable learning dynamics. This study investigates the utilization of Genetic Algorithms (GAs) as a mechanism for improving RL performance in an industrially inspired sorting environment. We propose a novel approach in which GA-generated expert demonstrations are used to enhance policy learning. These demonstrations are incorporated into a Deep Q-Network (DQN) replay buffer for experience-based learning and utilized as warm-start trajectories for Proximal Policy Optimization (PPO) agents to accelerate training convergence. Our experiments compare standard RL training with rule-based heuristics, brute-force optimization, and demonstration data, revealing that GA-derived demonstrations significantly improve RL performance. Notably, PPO agents initialized with GA-generated data achieved superior cumulative rewards, highlighting the potential of hybrid learning paradigms, where heuristic search methods complement data-driven RL. The utilized framework is publicly available and enables further research into adaptive RL strategies for real-world applications.

cs.LG↗
arXiv2025

A Superlinearly Convergent Evolution Strategy

We present a hybrid algorithm between an evolution strategy and a quasi Newton method. The design is based on the Hessian Estimation Evolution Strategy, which iteratively estimates the inverse square root of the Hessian matrix of the problem. This is akin to a quasi-Newton method and corresponding derivative-free trust-region algorithms like NEWUOA. The proposed method therefore replaces the global recombination step commonly found in non-elitist evolution strategies with a quasi-Newton step. Numerical results show superlinear convergence, resulting in improved performance in particular on smooth convex problems.

math.OC↗
arXiv2025

Deep Reinforcement Learning Based Navigation with Macro Actions and Topological Maps

This paper addresses the challenge of navigation in large, visually complex environments with sparse rewards. We propose a method that uses object-oriented macro actions grounded in a topological map, allowing a simple Deep Q-Network (DQN) to learn effective navigation policies. The agent builds a map by detecting objects from RGBD input and selecting discrete macro actions that correspond to navigating to these objects. This abstraction drastically reduces the complexity of the underlying reinforcement learning problem and enables generalization to unseen environments. We evaluate our approach in a photorealistic 3D simulation and show that it significantly outperforms a random baseline under both immediate and terminal reward conditions. Our results demonstrate that topological structure and macro-level abstraction can enable sample-efficient learning even from pixel data.

cs.LG↗
arXiv2025

Curriculum RL meets Monte Carlo Planning: Optimization of a Real World Container Management Problem

In this work, we augment reinforcement learning with an inference-time collision model to ensure safe and efficient container management in a waste-sorting facility with limited processing capacity. Each container has two optimal emptying volumes that trade off higher throughput against overflow risk. Conventional reinforcement learning (RL) approaches struggle under delayed rewards, sparse critical events, and high-dimensional uncertainty -- failing to consistently balance higher-volume empties with the risk of safety-limit violations. To address these challenges, we propose a hybrid method comprising: (1) a curriculum-learning pipeline that incrementally trains a PPO agent to handle delayed rewards and class imbalance, and (2) an offline pairwise collision model used at inference time to proactively avert collisions with minimal online cost. Experimental results show that our targeted inference-time collision checks significantly improve collision avoidance, reduce safety-limit violations, maintain high throughput, and scale effectively across varying container-to-PU ratios. These findings offer actionable guidelines for designing safe and efficient container-management systems in real-world facilities.

cs.LG↗
arXiv2025

SortingEnv: An Extendable RL-Environment for an Industrial Sorting Process

We present a novel reinforcement learning (RL) environment designed to both optimize industrial sorting systems and study agent behavior in evolving spaces. In simulating material flow within a sorting process our environment follows the idea of a digital twin, with operational parameters like belt speed and occupancy level. To reflect real-world challenges, we integrate common upgrades to industrial setups, like new sensors or advanced machinery. It thus includes two variants: a basic version focusing on discrete belt speed adjustments and an advanced version introducing multiple sorting modes and enhanced material composition observations. We detail the observation spaces, state update mechanisms, and reward functions for both environments. We further evaluate the efficiency of common RL algorithms like Proximal Policy Optimization (PPO), Deep-Q-Networks (DQN), and Advantage Actor Critic (A2C) in comparison to a classical rule-based agent (RBA). This framework not only aids in optimizing industrial processes but also provides a foundation for studying agent behavior and transferability in evolving environments, offering insights into model performance and practical implications for real-world RL applications.

cs.LG↗
arXiv2024

Variable Metric Evolution Strategies for High-dimensional Multi-Objective Optimization

We design a class of variable metric evolution strategies well suited for high-dimensional problems. We target problems with many variables, not (necessarily) with many objectives. The construction combines two independent developments: efficient algorithms for scaling covariance matrix adaptation to high dimensions, and evolution strategies for multi-objective optimization. In order to design a specific instance of the class we first develop a (1+1) version of the limited memory matrix adaptation evolution strategy and then use an established standard construction to turn a population thereof into a state-of-the-art multi-objective optimizer with indicator-based selection. The method compares favorably to adaptation of the full covariance matrix.

cs.NE↗
arXiv2024

Deep-learning-based identification of individual motion characteristics from upper-limb trajectories towards disorder stage evaluation

The identification of individual movement characteristics sets the foundation for the assessment of personal rehabilitation progress and can provide diagnostic information on levels and stages of movement disorders. This work presents a preliminary study for differentiating individual motion patterns using a dataset of 3D upper-limb transport trajectories measured in task-space. Identifying individuals by deep time series learning can be a key step to abstracting individual motion properties. In this study, a classification accuracy of about 95% is reached for a subset of nine, and about 78% for the full set of 31 individuals. This provides insights into the separability of patient attributes by exerting a simple standardized task to be transferred to portable systems.

cs.NE↗
arXiv2024

Solving a Real-World Optimization Problem Using Proximal Policy Optimization with Curriculum Learning and Reward Engineering

We present a proximal policy optimization (PPO) agent trained through curriculum learning (CL) principles and meticulous reward engineering to optimize a real-world high-throughput waste sorting facility. Our work addresses the challenge of effectively balancing the competing objectives of operational safety, volume optimization, and minimizing resource usage. A vanilla agent trained from scratch on these multiple criteria fails to solve the problem due to its inherent complexities. This problem is particularly difficult due to the environment's extremely delayed rewards with long time horizons and class (or action) imbalance, with important actions being infrequent in the optimal policy. This forces the agent to anticipate long-term action consequences and prioritize rare but rewarding behaviours, creating a non-trivial reinforcement learning task. Our five-stage CL approach tackles these challenges by gradually increasing the complexity of the environmental dynamics during policy transfer while simultaneously refining the reward mechanism. This iterative and adaptable process enables the agent to learn a desired optimal policy. Results demonstrate that our approach significantly improves inference-time safety, achieving near-zero safety violations in addition to enhancing waste sorting plant efficiency.

cs.LG↗
arXiv2024

GET: A Generative EEG Transformer for Continuous Context-Based Neural Signals

Generating continuous electroencephalography (EEG) signals through advanced artificial neural networks presents a novel opportunity to enhance brain-computer interface (BCI) technology. This capability has the potential to significantly enhance applications ranging from simulating dynamic brain activity and data augmentation to improving real-time epilepsy detection and BCI inference. By harnessing generative transformer neural networks, specifically designed for EEG signal generation, we can revolutionize the interpretation and interaction with neural data. Generative AI has demonstrated significant success across various domains, from natural language processing (NLP) and computer vision to content creation in visual arts and music. It distinguishes itself by using large-scale datasets to construct context windows during pre-training, a technique that has proven particularly effective in NLP, where models are fine-tuned for specific downstream tasks after extensive foundational training. However, the application of generative AI in the field of BCIs, particularly through the development of continuous, context-rich neural signal generators, has been limited. To address this, we introduce the Generative EEG Transformer (GET), a model leveraging transformer architecture tailored for EEG data. The GET model is pre-trained on diverse EEG datasets, including motor imagery and alpha wave datasets, enabling it to produce high-fidelity neural signals that maintain contextual integrity. Our empirical findings indicate that GET not only faithfully reproduces the frequency spectrum of the training data and input prompts but also robustly generates continuous neural signals. By adopting the successful training strategies of the NLP domain for BCIs, the GET sets a new standard for the development and application of neural signal generation technologies.

q-bio.NC↗
arXiv2024

ProtoP-OD: Explainable Object Detection with Prototypical Parts

Interpretation and visualization of the behavior of detection transformers tends to highlight the locations in the image that the model attends to, but it provides limited insight into the \emph{semantics} that the model is focusing on. This paper introduces an extension to detection transformers that constructs prototypical local features and uses them in object detection. These custom features, which we call prototypical parts, are designed to be mutually exclusive and align with the classifications of the model. The proposed extension consists of a bottleneck module, the prototype neck, that computes a discretized representation of prototype activations and a new loss term that matches prototypes to object classes. This setup leads to interpretable representations in the prototype neck, allowing visual inspection of the image content perceived by the model and a better understanding of the model's reliability. We show experimentally that our method incurs only a limited performance penalty, and we provide examples that demonstrate the quality of the explanations provided by our method, which we argue outweighs the performance penalty.

cs.CV↗
arXiv2023

Ruhr Hand Motion Catalog of Human Center-Out Transport Trajectories in 3D Task-Space Captured by a Redundant Measurement System

Neurological conditions are a major source of movement disorders. Motion modelling and variability analysis have the potential to identify pathology but require profound data. We introduce a systematic dataset of 3D center-out task-space trajectories of human hand transport movements in a natural setting. The transport tasks of this study consist of grasping a cylindric object from a unified start position and transporting it to one of nine target locations in unconstrained operational space. The measurement procedure is automatized to record ten trials per target location. With that, the dataset consists of 90 movement trajectories for each hand of 31 participants without known movement disorders. The participants are aged between 21 and 78 years, covering a wide range. Data are recorded redundantly by both an optical tracking system and an IMU sensor. As opposed to the stationary capturing system, the IMU can be considered as a portable, low-cost and energy-efficient alternative to be implemented on embedded systems.

q-bio.QM↗