More Like this

1. StarCraftImage: A Dataset For Prototyping Spatial Reasoning Methods For Multi-Agent Environments

   https://doi.org/10.6084/m9.figshare.22974983.v2  

   Kulinski, Sean; Waytowich, Nicholas; Hare, James; Inouye, David (January 2023, figshare)

   Fine-grained visual reasoning tasks in multi-agent environments such as event prediction, agent type identification, or missing data imputation are important for multiple applications (e.g., autonomous surveillance over sensor networks and subtasks for reinforcement learning (RL)). StarCraft II game replays encode intelligent (and adversarial) multi-agent behavior and could provide a testbed for these tasks; however, extracting simple and standardized representations for prototyping these tasks is laborious and hinders reproducibility. In contrast, MNIST and CIFAR10, despite their extreme simplicity, have enabled rapid prototyping and reproducibility of ML methods. Following the simplicity of these datasets, we construct a benchmark fine-grained multi-agent categorization dataset based on StarCraft II replays that exhibit complex multi-agent behaviors, while still being as easy to use as MNIST and CIFAR10. Specifically, we carefully summarize a window of 255 consecutive game states to create 3.6 million summary images from 60,000 replays, including all relevant metadata such as game outcome and player races. We develop three formats of decreasing complexity: Hyperspectral images that include one channel for every unit type (similar to multispectral geospatial images), RGB images that mimic CIFAR10, and grayscale images that mimic MNIST. We show how this dataset can be used for prototyping fine-grained multi-agent categorization methods. All datasets, code for extraction, and code for dataset loading can be found at https://starcraftdata.davidinouye.com/.</p> 

   more » « less
2. Trustworthy Contextual Neural Networks for Deciphering Fracture in Metals

   https://doi.org/10.1111/ffe.14686  

   Arumugam, Dharanidharan; Kiran, Ravi (May 2025, Fatigue & Fracture of Engineering Materials & Structures)

   ABSTRACT A novel approach was proposed and implemented to assess the confidence of the individual class predictions made by convolutional neural networks trained to identify the type of fracture in metals. This approach involves utilizing contextual evidence in the form of contextual fracture images and contextual scores, which serve as indicators for determining the certainty of the predictions. This approach was first tested on both shallow and deep convolutional neural networks employing four publicly available image datasets: MNIST, EMNIST, FMNIST, and CIFAR10, and subsequently validated on an in‐house steel fracture dataset—FRAC, containing ductile and brittle fracture images. The effectiveness of the method is validated by producing contextual images and scores for the fracture image data and other image datasets to assess the confidence of selected predictions from the datasets. The CIFAR‐10 dataset yielded the lowest mean contextual score of 78 for the shallow model, with over 50% of representative test instances receiving a score below 90, indicating lower confidence in the model's predictions. In contrast, the CNN model used for the fracture dataset achieved a mean contextual score of 99, with 0% of representative test instances receiving a score below 90, suggesting a high level of confidence in its predictions. This approach enhances the interpretability of trained convolutional neural networks and provides greater insight into the confidence of their outputs. 

   more » « less
3. Where to Diffuse, How to Diffuse and How to Get Back: Automated Learning in Multivariate Diffusions

   Singhal, Raghav; Goldstein, Mark; Ranganath, Rajesh (May 2023, International Conference on Learning Representations)

   Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality. For example, extending the inference process with auxiliary variables leads to improved sample quality. While there are many such multivariate diffusions to explore, each new one requires significant model-specific analysis, hindering rapid prototyping and evaluation. In this work, we study Multivariate Diffusion Models (MDMs). For any number of auxiliary variables, we provide a recipe for maximizing a lower-bound on the MDMs likelihood without requiring any model-specific analysis. We then demonstrate how to parameterize the diffusion for a specified target noise distribution; these two points together enable optimizing the inference diffusion process. Optimizing the diffusion expands easy experimentation from just a few well-known processes to an automatic search over all linear diffusions. To demonstrate these ideas, we introduce two new specific diffusions as well as learn a diffusion process on the MNIST, CIFAR10, and ImageNet32 datasets. We show learned MDMs match or surpass bits-per-dims (BPDs) relative to fixed choices of diffusions for a given dataset and model architecture. 

   more » « less
4. Value-Decomposition Multi-Agent Actor-Critics

   Su, Jianyu; Adams, Stephen; Beling, Peter (February 2021, Proceedings of the AAAI Conference on Artificial Intelligence)

   The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negative function approximator and achieves the best performance on the StarCraft II micromanagement testbed, a common MARL benchmark. However, our experiments demonstrate that, in some cases, QMIX performs sub-optimally with the A2C framework, a training paradigm that promotes algorithm training efficiency. To obtain a reasonable trade-off between training efficiency and algorithm performance, we extend value-decomposition to actor-critic methods that are compatible with A2C and propose a novel actor-critic framework, value-decomposition actor-critic (VDAC). We evaluate VDAC on the StarCraft II micromanagement task and demonstrate that the proposed framework improves median performance over other actor-critic methods. Furthermore, we use a set of ablation experiments to identify the key factors that contribute to the performance of VDAC. 

   more » « less
5. Value-decomposition multi-agent actor-critics

   Su, Jianyu; Adams, Stephen; Beling, Peter (February 2021, Proceedings of the AAAI Conference on Artificial Intelligence)

   The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negative function approximator and achieves the best performance on the StarCraft II micromanagement testbed, a common MARL benchmark. However, our experiments demonstrate that, in some cases, QMIX performs sub-optimally with the A2C framework, a training paradigm that promotes algorithm training efficiency. To obtain a reasonable trade-off between training efficiency and algorithm performance, we extend value-decomposition to actor-critic methods that are compatible with A2C and propose a novel actor-critic framework, value-decomposition actor-critic (VDAC). We evaluate VDAC on the StarCraft II micromanagement task and demonstrate that the proposed framework improves median performance over other actor-critic methods. Furthermore, we use a set of ablation experiments to identify the key factors that contribute to the performance of VDAC. 

   more » « less