Embedding Safety into RL: A New Take on Trust Region Methods

Reinforcement Learning (RL) agents are able to solve a wide variety of tasks but are prone to producing unsafe behaviors. Constrained Markov Decision Processes (CMDPs) provide a popular framework for incorporating safety constraints. However, common solution methods often compromise reward maximization by being overly conservative or allow unsafe behavior during training. We propose Constrained Trust Region Policy Optimization (C-TRPO), a novel approach that modifies the geometry of the policy space based on the safety constraints and yields trust regions composed exclusively of safe policies, ensuring constraint satisfaction throughout training. We theoretically study the convergence and update properties of C-TRPO and highlight connections to TRPO, Natural Policy Gradient (NPG), and Constrained Policy Optimization (CPO). Finally, we demonstrate experimentally that C-TRPO significantly reduces constraint violations while achieving competitive reward maximization compared to state-of-the-art CMDP algorithms.

Revealing the learning process in reinforcement learning agents through attention-oriented metrics

The learning process of a reinforcement learning (RL) agent remains poorly understood beyond the mathematical formulation of its learning algorithm. To address this gap, we introduce attention-oriented metrics (ATOMs) to investigate the development of an RL agent's attention during training. We tested ATOMs on three variations of a Pong game, each designed to teach the agent distinct behaviours, complemented by a behavioural assessment. Our findings reveal that ATOMs successfully delineate the attention patterns of an agent trained on each game variation, and that these differences in attention patterns translate into differences in the agent's behaviour. Through continuous monitoring of ATOMs during training, we observed that the agent's attention developed in phases, and that these phases were consistent across games. Finally, we noted that the agent's attention to its paddle emerged relatively late in the training and coincided with a marked increase in its performance score. Overall, we believe that ATOMs could significantly enhance our understanding of RL agents' learning processes, which is essential for improving their reliability and efficiency.

Open Problem: Active Representation Learning

In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous Localization and Mapping (active SLAM), and translate them to scientific discovery problems, exemplified by adaptive microscopy. We explore the need for a framework that derives exploration skills from representations that are in some sense actionable, aiming to enhance the efficiency and effectiveness of data collection and model building in the natural sciences.

Quality control for more reliable integration of deep learning-based image segmentation into medical workflows

Machine learning algorithms underpin modern diagnostic-aiding software, which has proved valuable in clinical practice, particularly in radiology. However, inaccuracies, mainly due to the limited availability of clinical samples for training these algorithms, hamper their wider applicability, acceptance, and recognition amongst clinicians. We present an analysis of state-of-the-art automatic quality control (QC) approaches that can be implemented within these algorithms to estimate the certainty of their outputs. We validated the most promising approaches on a brain image segmentation task identifying white matter hyperintensities (WMH) in magnetic resonance imaging data. WMH are a correlate of small vessel disease common in mid-to-late adulthood and are particularly challenging to segment due to their varied size, and distributional patterns. Our results show that the aggregation of uncertainty and Dice prediction were most effective in failure detection for this task. Both methods independently improved mean Dice from 0.82 to 0.84. Our work reveals how QC methods can help to detect failed segmentation cases and therefore make automatic segmentation more reliable and suitable for clinical practice.

A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data

In recent years, Convolutional Neural Networks (CNNs) have become the state-of-the-art method for biomedical image analysis. However, these networks are usually trained in a supervised manner, requiring large amounts of labelled training data. These labelled data sets are often difficult to acquire in the biomedical domain. In this work, we validate alternative ways to train CNNs with fewer labels for biomedical image segmentation using. We adapt two semi- and self-supervised image classification methods and analyse their performance for semantic segmentation of biomedical microscopy images.

Convolutional neural network stacking for medical image segmentation in CT scans

Computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks(CNNs). The main challenges in handling CT scans with CNN are the scale of data (large range of Hounsfield Units) and the processing of the slices. In this paper, we consider a framework, which addresses these demands regarding the data pre-processing, the data augmentation, and the CNN architecture itself. For this purpose, we present a data preprocessing and an augmentation method tailored to CT data. We evaluate and compare different input dimensionalities and two different CNN architectures. One of the architectures is a modified U-Net and the other a modified Mixed-Scale Dense Network (MS-D Net). Thus, we compare dilated convolutions for parallel multi-scale processing to the U-Net approach with traditional scaling operations based on the different input dimensionalities. Finally, we merge a set of 3D modified MS-D Nets and a set of 2D modified U-Nets as a stacked CNN-model to combine the different strengths of both model.