Abstract:Monte Carlo (MC) simulations, particularly using FLUKA, are essential for replicating real-world scenarios across scientific and engineering fields. Despite the robustness and versatility, FLUKA faces significant limitations in automation and integration with external post-processing tools, leading to workflows with a steep learning curve, which are time-consuming and prone to human errors. Traditional methods involving the use of shell and Python scripts, MATLAB, and Microsoft Excel require extensive manual intervention and lack flexibility, adding complexity to evolving scenarios. This study explores the potential of Large Language Models (LLMs) and AI agents to address these limitations. AI agents, integrate natural language processing with autonomous reasoning for decision-making and adaptive planning, making them ideal for automation. We introduce AutoFLUKA, an AI agent application developed using the LangChain Python Framework to automate typical MC simulation workflows in FLUKA. AutoFLUKA can modify FLUKA input files, execute simulations, and efficiently process results for visualization, significantly reducing human labor and error. Our case studies demonstrate that AutoFLUKA can handle both generalized and domain-specific cases, such as Microdosimetry, with an streamlined automated workflow, showcasing its scalability and flexibility. The study also highlights the potential of Retrieval Augmentation Generation (RAG) tools to act as virtual assistants for FLUKA, further improving user experience, time and efficiency. In conclusion, AutoFLUKA represents a significant advancement in automating MC simulation workflows, offering a robust solution to the inherent limitations. This innovation not only saves time and resources but also opens new paradigms for research and development in high energy physics, medical physics, nuclear engineering space and environmental science.
Abstract:The study focuses on developing a digital twin testbed tailored for public safety technologies, incorporating simulated wireless communication within the digital world. The integration enables rapid analysis of signal strength, facilitating effective communication among personnel during catastrophic incidents in the virtual environment. The virtual world also helps with the training of first responders. The digital environment is constructed using the actual training facility for first responders as a blueprint. Using the photo-reference method, we meticulously constructed all buildings and objects within this environment. These reconstructed models are precisely placed relative to their real-world counterparts. Subsequently, all structures and objects are integrated into the Unreal Engine (UE) to create an interactive environment tailored specifically to the requirements of first responders.
Abstract:This study presents a novel mechanical metallic reflector array to guide wireless signals to the point of interest, thereby enhancing received signal quality. Comprised of numerous individual units, this device, which acts as a linear Fresnel reflector (LFR), facilitates the reflection of incoming signals to a desired location. Leveraging geometric principles, we present a systematic approach for redirecting beams from an Access Point (AP) toward User Equipment (UE) positions. This methodology is geared towards optimizing beam allocation, thereby maximizing the number of beams directed towards the UE. Ray tracing simulations conducted for two 3D wireless communication scenarios demonstrate significant increases in path gains and received signal strengths (RSS) by at least 50dB with strategically positioned devices.
Abstract:Reinforcement learning struggles in the face of long-horizon tasks and sparse goals due to the difficulty in manual reward specification. While existing methods address this by adding intrinsic rewards, they may fail to provide meaningful guidance in long-horizon decision-making tasks with large state and action spaces, lacking purposeful exploration. Inspired by human cognition, we propose a new multi-modal model-based RL approach named Dreaming with Large Language Models (DLLM). DLLM integrates the proposed hinting subgoals from the LLMs into the model rollouts to encourage goal discovery and reaching in challenging tasks. By assigning higher intrinsic rewards to samples that align with the hints outlined by the language model during model rollouts, DLLM guides the agent toward meaningful and efficient exploration. Extensive experiments demonstrate that the DLLM outperforms recent methods in various challenging, sparse-reward environments such as HomeGrid, Crafter, and Minecraft by 27.7\%, 21.1\%, and 9.9\%, respectively.
Abstract:Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network Distillation (RND) algorithm has been demonstrated to be effective in numerous environments, it often needs more discriminative power in bonus allocation. This paper highlights the ``bonus inconsistency'' issue within RND, pinpointing its primary limitation. To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND. DRND enhances the exploration process by distilling a distribution of random networks and implicitly incorporating pseudo counts to improve the precision of bonus allocation. This refinement encourages agents to engage in more extensive exploration. Our method effectively mitigates the inconsistency issue without introducing significant computational overhead. Both theoretical analysis and experimental results demonstrate the superiority of our approach over the original RND algorithm. Our method excels in challenging online exploration scenarios and effectively serves as an anti-exploration mechanism in D4RL offline tasks.
Abstract:Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to fine-tune the underlying models. However, crafting an efficient reward model demands extensive datasets, optimal architecture, and manual hyperparameter tuning, making the process both time and cost-intensive. The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model. However, the extensive GPU memory requirement of the diffusion model's denoising process hinders the direct application of the DPO method. To address this issue, we introduce the Direct Preference for Denoising Diffusion Policy Optimization (D3PO) method to directly fine-tune diffusion models. The theoretical analysis demonstrates that although D3PO omits training a reward model, it effectively functions as the optimal reward model trained using human feedback data to guide the learning process. This approach requires no training of a reward model, proving to be more direct, cost-effective, and minimizing computational overhead. In experiments, our method uses the relative scale of objectives as a proxy for human preference, delivering comparable results to methods using ground-truth rewards. Moreover, D3PO demonstrates the ability to reduce image distortion rates and generate safer images, overcoming challenges lacking robust reward models. Our code is publicly available in https://github.com/yk7333/D3PO/tree/main.
Abstract:Lossy compression has become an important technique to reduce data size in many domains. This type of compression is especially valuable for large-scale scientific data, whose size ranges up to several petabytes. Although Autoencoder-based models have been successfully leveraged to compress images and videos, such neural networks have not widely gained attention in the scientific data domain. Our work presents a neural network that not only significantly compresses large-scale scientific data but also maintains high reconstruction quality. The proposed model is tested with scientific benchmark data available publicly and applied to a large-scale high-resolution climate modeling data set. Our model achieves a compression ratio of 140 on several benchmark data sets without compromising the reconstruction quality. Simulation data from the High-Resolution Community Earth System Model (CESM) Version 1.3 over 500 years are also being compressed with a compression ratio of 200 while the reconstruction error is negligible for scientific analysis.
Abstract:Magnetic resonance imaging (MRI) is one of the noninvasive imaging modalities that can produce high-quality images. However, the scan procedure is relatively slow, which causes patient discomfort and motion artifacts in images. Accelerating MRI hardware is constrained by physical and physiological limitations. A popular alternative approach to accelerated MRI is to undersample the k-space data. While undersampling speeds up the scan procedure, it generates artifacts in the images, and advanced reconstruction algorithms are needed to produce artifact-free images. Recently deep learning has emerged as a promising MRI reconstruction method to address this problem. However, straightforward adoption of the existing deep learning neural network architectures in MRI reconstructions is not usually optimal in terms of efficiency and reconstruction quality. In this work, MRI reconstruction from undersampled data was carried out using an optimized neural network using a novel evolutionary neural architecture search algorithm. Brain and knee MRI datasets show that the proposed algorithm outperforms manually designed neural network-based MR reconstruction models.