Partially observable environments present increased decisionmaking complexity for Reinforcement Learning agents. This paper explores methods for improving automated decision-making in partially observable environments by utilizing Variational Auto-Encoders (VAEs) trained on expert demonstrations to generate intrinsic rewards for reinforcement learning (RL) agents. Specifically, a VAE is pre-trained on expert demonstrations to construct a latent representation of successful decision-making. This latent representation is utilized to generate intrinsic rewards via KL-divergence, augmenting the extrinsic reward signal during Proximal Policy Optimization (PPO) training. Experiments are conducted using a symbolic-matching navigation task within a Unity MLAgents environment, which requires memory formation and hierarchical reasoning. Results indicate that incorporating demonstration-based intrinsic rewards improves the learning efficiency and convergence of PPO agents compared to baseline models without intrinsic rewards. The findings suggest that latent-space representations from demonstrations can effectively guide exploration in challenging RL scenarios, and that certain behaviors are retained from demonstrations.

Hematologic cancers are among the most common cancers in adults and children. Despite significant improvements in therapies, many patients still succumb to the disease. Therefore, novel therapies are needed. The Wiskott-Aldrich syndrome protein (WASp) family regulates actin assembly in conjunction with the Arp2/3 complex, a ubiquitous nucleation factor. WASp is expressed exclusively in hematopoietic cells and exists in two allosteric conformations: autoinhibited or activated. Here, we describe the development of EG-011, a first-in-class small molecule activator of the autoinhibited form of WASp. EG-011 possesses in vitro and in vivo antitumor activity as a single agent in lymphoma, leukemia, and multiple myeloma, including models of secondary resistance to PI3K, BTK, and proteasome inhibitors. The in vitro activity was confirmed in a lymphoma xenograft. Actin polymerization and WASp binding were demonstrated using multiple techniques. Transcriptome analysis highlighted homology with drugs inducing actin polymerization.

Automatic checkout systems are designed to predict a complete shopping receipt using an image from the checkout area. These systems require high classification accuracy across numerous classes and must operate in real-time, despite domain differences between training data and real-world conditions. Building on recent advancements, we propose a method that outperforms current solutions and can be applied in real-time in automatic checkout systems. Our method leverages the Segment Anything Model to extract high-quality masks from lab product images, which are then transformed into synthetic checkout images and adapted to the real domain using contrastive unpaired translation. We train a product recognition model with data augmentation, named SCA+Y8, and further improve it through fine-tuning with pseudo-labels from unlabeled checkout images, resulting in an improved model called SCAFT+Y8. SCAFT+Y8 achieves a great increase in state-of-the-art performance, with an average receipt classification accuracy of 97.58%, and shows strong performance in smaller models, indicating the potential for deployment on low-cost edge devices.

Introduction: This study aimed to quantify the relationship between prosthetic users’ emotional response to prosthesis aesthetics and specific product properties. Methods: Words representing prosthesis users’ emotional response (Kansei) to different aesthetic designs of prostheses were identified via interviews and mood boards. A group of experts consolidated the words into thematic groups, each represented by a single, high-level ‘Kansei’ word. 53 lower limb prosthesis users completed a questionnaire, rating their perception of 13 aesthetic designs using the ‘Kansei’ words. Quantification Theory Type 1 was applied to explore the relationship between words and product properties. Sub-analyses assessed for differences based on sex, age and level of extroversion. Results: 5 high-level Kansei words were identified (‘Natural’, ‘Technological’, ‘Cool’, ‘Unique’ and ‘Functional’). The Kansei word ‘Natural’ had a strong association with realistic looking prostheses while the words ‘Technological’, ‘Cool’ and ‘Unique’ were strongly associated with expressive designs which incorporate hard, colourful covers. The word ‘Functional’ was not a reliable predictor of product properties. No major differences were observed within sub-grouped categories. Conclusion: Kansei words identified in this study can be used to help guide clients in their aesthetic design choices and to assist designers in achieving the desired response from their products.

Automatic recognition of grocery products can be used to improve customer flow at checkouts and reduce labor costs and store losses. Product recognition is, however, a challenging task for machine learning-based solutions due to the large number of products and their variations in appearance. In this work, we tackle the challenge of fine-grained product recognition by first extracting a large dataset from a grocery store containing products that are only differentiable by subtle details. Then, we propose a multimodal product recognition approach that uses product images with extracted OCR text from packages to improve fine-grained recognition of grocery products. We evaluate several image and text models separately and then combine them using different multimodal models of varying complexities. The results show that image and textual information complement each other in multimodal models and enable a classifier with greater recognition performance than unimodal models, especially when the number of training samples is limited. Therefore, this approach is suitable for many different scenarios in which product recognition is used to further improve recognition performance. The dataset can be found at https://github.com/Tubbias/finegrainocr .

This study explores the effects of incorporating demonstrations as pre-training of an improved Deep Q-Network (DQN). Inspiration is taken from methods such as Deep Q-learning from Demonstrations (DQfD), but instead of retaining the demonstrations throughout the training, the performance and behavioral effects of the policy when using demonstrations solely as pre-training are studied. A comparative experiment is performed on two game environments, Gymnasium's Car Racing and Atari Space Invaders. While demonstration pre-training in Car Racing shows improved learning efficacy, as indicated by higher evaluation and training rewards, these improvements do not show in Space Invaders, where it instead under-performed. This divergence suggests that the nature of a game's reward structure influences the effectiveness of demonstration pre-training. Interestingly, despite less pronounced quantitative differences, qualitative observations suggested distinctive strategic behaviors, notably in target elimination patterns in Space Invaders. These retained behaviors seem to get forgotten during extended training. The results show that we need to investigate further how exploration functions affect the effectiveness of demonstration pre-training, how behaviors can be retained without explicitly making the agent mimic demonstrations, and how non-optimal demonstrations can be incorporated for more stable learning with demonstrations.

Practitioners of multi-objective optimization currently lack open tools that provide decision support through knowledge discovery. There exist many software platforms for multi-objective optimization, but they often fall short of implementing methods for rigorous post-optimality analysis and knowledge discovery from the generated solutions. This paper presents Mimer, a multi-criteria decision support tool for solution exploration, preference elicitation, knowledge discovery, and knowledge visualization. Mimer is openly available as a web-based tool and uses state-of-the-art web-technologies based on WebAssembly to perform heavy computations on the client-side. Its features include multiple linked visualizations and input methods that enable the decision maker to interact with the solutions, knowledge discovery through interactive data mining and graph-based knowledge visualization. It also includes a complete Python programming interface for advanced data manipulation tasks that may be too specific for the graphical interface. Mimer is evaluated through a user study in which the participants are asked to perform representative tasks simulating practical analysis and decision making. The participants also complete a questionnaire about their experience and the features available in Mimer. The survey indicates that participants find Mimer useful for decision support. The participants also offered suggestions for enhancing some features and implementing new features to extend the capabilities of the tool.

Visualization researchers and visualization professionals seek appropriate abstractions of visualization requirements that permit considering visualization solutions independently from specific problems. Abstractions can help us design, analyze, organize, and evaluate the things we create. The literature has many task structures (taxonomies, typologies, etc.), design spaces, and related "frameworks" that provide abstractions of the problems a visualization is meant to address. In this Visualization Viewpoints article, we introduce a different one, a problem space that complements existing frameworks by focusing on the needs that a visualization is meant to solve. We believe it provides a valuable conceptual tool for designing and discussing visualizations.

OTX015 has no significant effect on non-malignant human fibroblasts. (a) Representative pictures of human fibroblasts treated for 72 h with 500 nM OTX015 or DMSO control. Scale bar=100 µm. (b) Growth of fibroblasts treated with 500 nM OTX015 (black) or DMSO control (grey) monitored over 96 h using the xCELLigence system. The slope (1/h) of both curves was calculated, and did not show a significant difference (right) using the Student's t test.

Supplemental Table S1: Cell lines and growth medium.

Supplemental Figures S6. Supplemental Figures S6: OTX015 effects on the production of IL-4 and IL-10 in DLBCL cell lines.

OTX015 reduces cell proliferation and induces apoptosis in MYCN amplified human xenografts. (a) Representative pictures of IMR5 xenograft tumor sections stained with hematoxylin/eosin, and immunohistochemical staining for apoptotic cells (cleaved caspase 3) and proliferating cells (Mib-1/Ki 67) are shown. Scale bar=250 µm. The relative fraction of positively stained cells for cleaved caspase 3 (b) and Mib-1 (c) were calculated from three representative images from each xenograft tumor and are shown as box plots. Statistical difference between groups was assessed by Student's t test. * p < 0.05, ** p < 0.01, *** p < 0.001.

Differentially expressed genes in IMR5 cells after OTX015 and JQ1 treatment respectively

The execution of teamwork varies widely depending on the domain and task in question. Despite the considerable diversity of teams and their operation, researchers tend to aim for unified theories and models regardless of field. However, we argue that there is a need for translation and adaptation of the theoretical models to each specific domain. To this end, a case study was carried out on fighter pilots and it was investigated how teamwork is performed in this specialised and challenging environment, with a specific focus on the dependence on technology for these teams. The collaboration between the fighter pilots is described and analysed using a generic theoretical model for effective teamwork from the literature. The results show that domain-specific application and modification is needed in order for the model to capture fighter pilot's teamwork. The study provides deeper understanding of the working conditions for teams of pilots and gives design implications for how tactical support systems can enhance teamwork in the domain. Practitioner summary: This article presents a qualitative interview study with fighter pilots based on a generic theoretical teamwork model applied to the fighter domain. The purpose is to understand the conditions under which teams of fighter pilots work and to provide guidance for the design of future technological aids.

Supplemental Figures S1-2. Supplemental Figures S1: effects of OTX015 on cell cycle and cell growth in DLBCL cell lines. Supplemental Figures S2: effects of OTX015 on apoptosis in DLBCL cell lines.

Westermann et al. as well as Valentijn et al. MYCN target gene list and expression changes after OTX015 treatment as well as BRD4 binding

GSEA of cancer gene sets after treatment with OTX015 and/or JQ1(GSEA, Broad institute)

OTX015 effect on cell viability positively correlates with MYCN status. (a) IC50 of the IMR 5, Chp 134, Chp 212, SK N-BE(2), IMR-32, SK-N-BE, NB69, SK N AS and GI-M-EN neuroblastoma cell lines measured using MTT assays. (b) Maximum reduction of viability in IMR 5, Chp 134, Chp 212, SK N-BE(2), IMR-32, SK-N-BE, NB69, SK N AS and GI-M-EN cells treated for 72 h with 6 µM OTX015 and measured using MTT assays. (c) Relative MYCN mRNA (top) and protein (bottom) expression in all analyzed neuroblastoma cell lines. (d/e) The IC50 values of the cell lines shown in (a) were plotted against MYCN mRNA expression (d) or MYCN protein expression (e), which is shown in (c). Both graphs show weak anti-correlative tendencies in both cell lines (MYCN mRNA p=0.22, MYCN protein p=0.16).

GSEA of gene sets describing general cellular processes after treatment with OTX015 and/or JQ1(GSEA, Broad institute)