An important challenge for enabling the deployment of reinforcement learning (RL) algorithms in the real world is safety. This has resulted in the recent research field of Safe RL, which aims to learn optimal policies that are safe. One successful approach in that direction is probabilistic logic shields (PLS), a model-based Safe RL technique that uses formal specifications based on probabilistic logic programming, constraining an agent's policy to comply with those specifications in a probabilistic sense. However, safety is inherently a multi-agent concept, since real-world environments often involve multiple agents interacting simultaneously, leading to a complex system which is hard to control. Moreover, safe multi-agent RL (Safe MARL) is still underexplored. In order to address this gap, in this paper we ($i$) introduce Shielded MARL (SMARL) by extending PLS to MARL -- in particular, we introduce Probabilistic Logic Temporal Difference Learning (PLTD) to enable shielded independent Q-learning (SIQL), and introduce shielded independent PPO (SIPPO) using probabilistic logic policy gradients; ($ii$) show its positive effect and use as an equilibrium selection mechanism in various game-theoretic environments including two-player simultaneous games, extensive-form games, stochastic games, and some grid-world extensions in terms of safety, cooperation, and alignment with normative behaviors; and ($iii$) look into the asymmetric case where only one agent is shielded, and show that the shielded agent has a significant influence on the unshielded one, providing further evidence of SMARL's ability to enhance safety and cooperation in diverse multi-agent environments.
相關內容
Who is Helping Whom? Student Concerns about AI- Teacher Collaboration in Higher Education Classrooms
AI's integration into education promises to equip teachers with data-driven insights and intervene in student learning. Despite the intended advancements, there is a lack of understanding of interactions and emerging dynamics in classrooms where various stakeholders including teachers, students, and AI, collaborate. This paper aims to understand how students perceive the implications of AI in Education in terms of classroom collaborative dynamics, especially AI used to observe students and notify teachers to provide targeted help. Using the story completion method, we analyzed narratives from 65 participants, highlighting three challenges: AI decontextualizing of the educational context; AI-teacher cooperation with bias concerns and power disparities; and AI's impact on student behavior that further challenges AI's effectiveness. We argue that for effective and ethical AI-facilitated cooperative education, future AIEd design must factor in the situated nature of implementation. Designers must consider the broader nuances of the education context, impacts on multiple stakeholders, dynamics involving these stakeholders, and the interplay among potential consequences for AI systems and stakeholders. It is crucial to understand the values in the situated context, the capacity and limitations of both AI and humans for effective cooperation, and any implications to the relevant ecosystem.
Early detection of surgical complications allows for timely therapy and proactive risk mitigation. Machine learning (ML) can be leveraged to identify and predict patient risks for postoperative complications. We developed and validated the effectiveness of predicting postoperative complications using a novel surgical Variational Autoencoder (surgVAE) that uncovers intrinsic patterns via cross-task and cross-cohort presentation learning. This retrospective cohort study used data from the electronic health records of adult surgical patients over four years (2018 - 2021). Six key postoperative complications for cardiac surgery were assessed: acute kidney injury, atrial fibrillation, cardiac arrest, deep vein thrombosis or pulmonary embolism, blood transfusion, and other intraoperative cardiac events. We compared prediction performances of surgVAE against widely-used ML models and advanced representation learning and generative models under 5-fold cross-validation. 89,246 surgeries (49% male, median (IQR) age: 57 (45-69)) were included, with 6,502 in the targeted cardiac surgery cohort (61% male, median (IQR) age: 60 (53-70)). surgVAE demonstrated superior performance over existing ML solutions across all postoperative complications of cardiac surgery patients, achieving macro-averaged AUPRC of 0.409 and macro-averaged AUROC of 0.831, which were 3.4% and 3.7% higher, respectively, than the best alternative method (by AUPRC scores). Model interpretation using Integrated Gradients highlighted key risk factors based on preoperative variable importance. surgVAE showed excellent discriminatory performance for predicting postoperative complications and addressing the challenges of data complexity, small cohort sizes, and low-frequency positive events. surgVAE enables data-driven predictions of patient risks and prognosis while enhancing the interpretability of patient risk profiles.
Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation, but this turns out to be ineffective in maintaining safety constraints with high probability. To this end, we move to the quantile-constrained RL that enables a higher level of safety without any expectation-form approximations. We directly estimate the quantile gradients through sampling and provide the theoretical proofs of convergence. Then a tilted update strategy for quantile gradients is implemented to compensate the asymmetric distributional density, with a direct benefit of return performance. Experiments demonstrate that the proposed model fully meets safety requirements (quantile constraints) while outperforming the state-of-the-art benchmarks with higher return.
Developers rely on the static safety guarantees of the Rust programming language to write secure and performant applications. However, Rust is frequently used to interoperate with other languages which allow design patterns that conflict with Rust's evolving aliasing models. Miri is currently the only dynamic analysis tool that can validate applications against these models, but it does not support foreign functions, indicating that there may be a critical correctness gap across the Rust ecosystem. We conducted a large-scale evaluation of Rust libraries that call foreign functions to determine whether Miri's dynamic analyses remain useful in this context. We used Miri and an LLVM interpreter to jointly execute applications that call foreign functions, where we found 47 instances of undefined or undesired behavior from 37 libraries. Three bugs were found in libraries that had more than 10,000 daily downloads on average during our observation period, and one was found in a library maintained by the Rust Project. Many of these bugs were violations of Rust's aliasing models, but the latest Tree Borrows model was significantly more permissive than the earlier Stacked Borrows model. The Rust community must invest in new, production-ready tooling for multi-language applications to ensure that developers can detect these errors.
Recent advances in artificial intelligence (AI), in particular self-supervised learning of foundation models (FMs), are revolutionizing medical imaging and computational pathology (CPath). A constant challenge in the analysis of digital Whole Slide Images (WSIs) is the problem of aggregating tens of thousands of tile-level image embeddings to a slide-level representation. Due to the prevalent use of datasets created for genomic research, such as TCGA, for method development, the performance of these techniques on diagnostic slides from clinical practice has been inadequately explored. This study conducts a thorough benchmarking analysis of ten slide-level aggregation techniques across nine clinically relevant tasks, including diagnostic assessment, biomarker classification, and outcome prediction. The results yield following key insights: (1) Embeddings derived from domain-specific (histological images) FMs outperform those from generic ImageNet-based models across aggregation methods. (2) Spatial-aware aggregators enhance the performance significantly when using ImageNet pre-trained models but not when using FMs. (3) No single model excels in all tasks and spatially-aware models do not show general superiority as it would be expected. These findings underscore the need for more adaptable and universally applicable aggregation techniques, guiding future research towards tools that better meet the evolving needs of clinical-AI in pathology. The code used in this work is available at \url{//github.com/fuchs-lab-public/CPath_SABenchmark}.
Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-output neural network model by introducing a start-end channel separation mechanism and enhancing the feature fusion process. After training, the proposed NDR model can output a narrowly focused optimal probability distribution, referred to as the guideline, and a broadly distributed suboptimal distribution, referred to as the region. Subsequently, based on the guideline prediction, we calculate the continuous reward function for the Q-learning method, and based on the region prediction, we initialize the Q-table with a bias. We conducted training, validation, and path planning simulation experiments on public datasets. The results indicate that the NDR model outperforms previous methods by up to 5\% in prediction accuracy. Furthermore, the proposed NDR-QL method improves the convergence speed of the baseline Q-learning method by 90\% and also surpasses the previously improved Q-learning methods in path quality metrics.
Recent artificial intelligence (AI) systems have reached milestones in "grand challenges" ranging from Go to protein-folding. The capability to retrieve medical knowledge, reason over it, and answer medical questions comparably to physicians has long been viewed as one such grand challenge. Large language models (LLMs) have catalyzed significant progress in medical question answering; Med-PaLM was the first model to exceed a "passing" score in US Medical Licensing Examination (USMLE) style questions with a score of 67.2% on the MedQA dataset. However, this and other prior work suggested significant room for improvement, especially when models' answers were compared to clinicians' answers. Here we present Med-PaLM 2, which bridges these gaps by leveraging a combination of base LLM improvements (PaLM 2), medical domain finetuning, and prompting strategies including a novel ensemble refinement approach. Med-PaLM 2 scored up to 86.5% on the MedQA dataset, improving upon Med-PaLM by over 19% and setting a new state-of-the-art. We also observed performance approaching or exceeding state-of-the-art across MedMCQA, PubMedQA, and MMLU clinical topics datasets. We performed detailed human evaluations on long-form questions along multiple axes relevant to clinical applications. In pairwise comparative ranking of 1066 consumer medical questions, physicians preferred Med-PaLM 2 answers to those produced by physicians on eight of nine axes pertaining to clinical utility (p < 0.001). We also observed significant improvements compared to Med-PaLM on every evaluation axis (p < 0.001) on newly introduced datasets of 240 long-form "adversarial" questions to probe LLM limitations. While further studies are necessary to validate the efficacy of these models in real-world settings, these results highlight rapid progress towards physician-level performance in medical question answering.
As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in many tasks. One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data. In this survey, we frame DA methods into three categories based on the diversity of augmented data, including paraphrasing, noising, and sampling. Our paper sets out to analyze DA methods in detail according to the above categories. Further, we also introduce their applications in NLP tasks as well as the challenges.
Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing post hoc techniques to explain the predictions, giving rise to the area of explainability. Recently, explainability of deep models on images and texts has achieved significant progress. In the area of graph data, graph neural networks (GNNs) and their explainability are experiencing rapid developments. However, there is neither a unified treatment of GNN explainability methods, nor a standard benchmark and testbed for evaluations. In this survey, we provide a unified and taxonomic view of current GNN explainability methods. Our unified and taxonomic treatments of this subject shed lights on the commonalities and differences of existing methods and set the stage for further methodological developments. To facilitate evaluations, we generate a set of benchmark graph datasets specifically for GNN explainability. We summarize current datasets and metrics for evaluating GNN explainability. Altogether, this work provides a unified methodological treatment of GNN explainability and a standardized testbed for evaluations.
Few sample learning (FSL) is significant and challenging in the field of machine learning. The capability of learning and generalizing from very few samples successfully is a noticeable demarcation separating artificial intelligence and human intelligence since humans can readily establish their cognition to novelty from just a single or a handful of examples whereas machine learning algorithms typically entail hundreds or thousands of supervised samples to guarantee generalization ability. Despite the long history dated back to the early 2000s and the widespread attention in recent years with booming deep learning technologies, little surveys or reviews for FSL are available until now. In this context, we extensively review 200+ papers of FSL spanning from the 2000s to 2019 and provide a timely and comprehensive survey for FSL. In this survey, we review the evolution history as well as the current progress on FSL, categorize FSL approaches into the generative model based and discriminative model based kinds in principle, and emphasize particularly on the meta learning based FSL approaches. We also summarize several recently emerging extensional topics of FSL and review the latest advances on these topics. Furthermore, we highlight the important FSL applications covering many research hotspots in computer vision, natural language processing, audio and speech, reinforcement learning and robotic, data analysis, etc. Finally, we conclude the survey with a discussion on promising trends in the hope of providing guidance and insights to follow-up researches.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191