强化学习（RL）涉及在未知系统中执行探索性动作。这可以将学习代理放在危险且潜在的灾难性系统中。当前在RL中解决安全学习的方法同时权衡了安全探索和任务实现。在本文中，我们介绍了新一代的RL求解器，这些求解器学会最大程度地减少安全性违规行为，同时在安全政策可以容忍的范围内最大化任务奖励。我们的方法引入了一个新型的两人框架，用于安全RL，称为分配探索安全培训算法（DESTA）。 DESTA的核心是两种自适应代理之间的游戏：安全代理，其任务是最大程度地减少安全违规行为和任务代理，其目标是最大程度地提高环境奖励。具体而言，安全代理可以在任何给定点有选择地控制系统，以防止任务代理在任何其他州自由执行其策略时违反安全性。该框架使安全代理能够学会在培训和测试时间中最大程度地减少未来安全违规行为的某些行动，而任务代理人执行的动作可以最大程度地提高其他任何地方的任务绩效。从理论上讲，我们证明DESTA会汇合到稳定的点，从而最大程度地违反了对预验证的政策的行为。从经验上讲，我们表明了DESTA提高现有政策安全性的能力，其次，当对任务代理和安全代理人同时培训时，构建安全的RL政策。我们展示了DESTA在Lunar Lander和Openai Gym的Frozen Lake中的领先RL方法的出色表现。

The ability to distinguish between different movie scenes is critical for understanding the storyline of a movie. However, accurately detecting movie scenes is often challenging as it requires the ability to reason over very long movie segments. This is in contrast to most existing video recognition models, which are typically designed for short-range video analysis. This work proposes a State-Space Transformer model that can efficiently capture dependencies in long movie videos for accurate movie scene detection. Our model, dubbed TranS4mer, is built using a novel S4A building block, which combines the strengths of structured state-space sequence (S4) and self-attention (A) layers. Given a sequence of frames divided into movie shots (uninterrupted periods where the camera position does not change), the S4A block first applies self-attention to capture short-range intra-shot dependencies. Afterward, the state-space operation in the S4A block is used to aggregate long-range inter-shot cues. The final TranS4mer model, which can be trained end-to-end, is obtained by stacking the S4A blocks one after the other multiple times. Our proposed TranS4mer outperforms all prior methods in three movie scene detection datasets, including MovieNet, BBC, and OVSD, while also being $2\times$ faster and requiring $3\times$ less GPU memory than standard Transformer models. We will release our code and models.

Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications. This is often because off-policy RL algorithms suffer from distributional shift, due to mismatch between dataset and the target policy, leading to high variance and over-estimation of value functions. In this work, we propose variance regularization for offline RL algorithms, using stationary distribution corrections. We show that by using Fenchel duality, we can avoid double sampling issues for computing the gradient of the variance regularizer. The proposed algorithm for offline variance regularization (OVAR) can be used to augment any existing offline policy optimization algorithms. We show that the regularizer leads to a lower bound to the offline policy optimization objective, which can help avoid over-estimation errors, and explains the benefits of our approach across a range of continuous control domains when compared to existing state-of-the-art algorithms.

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs contain irrelevant and exogenous information. In this work, we study how information bottlenecks can be used to construct latent states efficiently in the presence of task-irrelevant information. We propose architectures that utilize variational and discrete information bottlenecks, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self-supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learned bottlenecks help predict only the relevant state while ignoring irrelevant information.

Artificial intelligence(AI) systems based on deep neural networks (DNNs) and machine learning (ML) algorithms are increasingly used to solve critical problems in bioinformatics, biomedical informatics, and precision medicine. However, complex DNN or ML models that are unavoidably opaque and perceived as black-box methods, may not be able to explain why and how they make certain decisions. Such black-box models are difficult to comprehend not only for targeted users and decision-makers but also for AI developers. Besides, in sensitive areas like healthcare, explainability and accountability are not only desirable properties of AI but also legal requirements -- especially when AI may have significant impacts on human lives. Explainable artificial intelligence (XAI) is an emerging field that aims to mitigate the opaqueness of black-box models and make it possible to interpret how AI systems make their decisions with transparency. An interpretable ML model can explain how it makes predictions and which factors affect the model's outcomes. The majority of state-of-the-art interpretable ML methods have been developed in a domain-agnostic way and originate from computer vision, automated reasoning, or even statistics. Many of these methods cannot be directly applied to bioinformatics problems, without prior customization, extension, and domain adoption. In this paper, we discuss the importance of explainability with a focus on bioinformatics. We analyse and comprehensively overview of model-specific and model-agnostic interpretable ML methods and tools. Via several case studies covering bioimaging, cancer genomics, and biomedical text mining, we show how bioinformatics research could benefit from XAI methods and how they could help improve decision fairness.

Quantum machine learning (QML) has received increasing attention due to its potential to outperform classical machine learning methods in various problems. A subclass of QML methods is quantum generative adversarial networks (QGANs) which have been studied as a quantum counterpart of classical GANs widely used in image manipulation and generation tasks. The existing work on QGANs is still limited to small-scale proof-of-concept examples based on images with significant down-scaling. Here we integrate classical and quantum techniques to propose a new hybrid quantum-classical GAN framework. We demonstrate its superior learning capabilities by generating $28 \times 28$ pixels grey-scale images without dimensionality reduction or classical pre/post-processing on multiple classes of the standard MNIST and Fashion MNIST datasets, which achieves comparable results to classical frameworks with 3 orders of magnitude less trainable generator parameters. To gain further insight into the working of our hybrid approach, we systematically explore the impact of its parameter space by varying the number of qubits, the size of image patches, the number of layers in the generator, the shape of the patches and the choice of prior distribution. Our results show that increasing the quantum generator size generally improves the learning capability of the network. The developed framework provides a foundation for future design of QGANs with optimal parameter set tailored for complex image generation tasks.

Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic vision. Most recent works focus on designing curricula based on difficulty levels in input samples or smoothing the feature maps. However, smoothing labels to control the learning utility in a curriculum manner is still unexplored. In this work, we design a paced curriculum by label smoothing (P-CBLS) using paced learning with uniform label smoothing (ULS) for classification tasks and fuse uniform and spatially varying label smoothing (SVLS) for semantic segmentation tasks in a curriculum manner. In ULS and SVLS, a bigger smoothing factor value enforces a heavy smoothing penalty in the true label and limits learning less information. Therefore, we design the curriculum by label smoothing (CBLS). We set a bigger smoothing value at the beginning of training and gradually decreased it to zero to control the model learning utility from lower to higher. We also designed a confidence-aware pacing function and combined it with our CBLS to investigate the benefits of various curricula. The proposed techniques are validated on four robotic surgery datasets of multi-class, multi-label classification, captioning, and segmentation tasks. We also investigate the robustness of our method by corrupting validation data into different severity levels. Our extensive analysis shows that the proposed method improves prediction accuracy and robustness.

Task agnostic generative pretraining (GPT) has recently proved promising for zero- and few-shot learning, gradually diverting attention from the expensive supervised learning paradigm. Although the community is accumulating knowledge as to capabilities of English-language autoregressive models such as GPT-3 adopting this generative approach, scholarship about these models remains acutely Anglocentric. Consequently, the community currently has serious gaps in its understanding of this class of models, their potential, and their societal impacts in diverse settings, linguistic traditions, and cultures. To alleviate this issue for Arabic, a collection of diverse languages and language varieties with more than $400$ million population, we introduce JASMINE, a suite of powerful Arabic autoregressive Transformer language models ranging in size between 300 million-13 billion parameters. We pretrain our new models with large amounts of diverse data (400GB of text) from different Arabic varieties and domains. We evaluate JASMINE extensively in both intrinsic and extrinsic settings, using a comprehensive benchmark for zero- and few-shot learning across a wide range of NLP tasks. We also carefully develop and release a novel benchmark for both automated and human evaluation of Arabic autoregressive models focused at investigating potential social biases, harms, and toxicity in these models. We aim to responsibly release our models with interested researchers, along with code for experimenting with them

Climate change has increased the intensity, frequency, and duration of extreme weather events and natural disasters across the world. While the increased data on natural disasters improves the scope of machine learning (ML) in this field, progress is relatively slow. One bottleneck is the lack of benchmark datasets that would allow ML researchers to quantify their progress against a standard metric. The objective of this short paper is to explore the state of benchmark datasets for ML tasks related to natural disasters, categorizing them according to the disaster management cycle. We compile a list of existing benchmark datasets introduced in the past five years. We propose a web platform - NADBenchmarks - where researchers can search for benchmark datasets for natural disasters, and we develop a preliminary version of such a platform using our compiled list. This paper is intended to aid researchers in finding benchmark datasets to train their ML models on, and provide general directions for topics where they can contribute new benchmark datasets.

The neural implementation of operant conditioning with few trials is unclear. We propose a Hippocampus-Inspired Cognitive Architecture (HICA) as a neural mechanism for operant conditioning. HICA explains a learning mechanism in which agents can learn a new behavior policy in a few trials, as mammals do in operant conditioning experiments. HICA is composed of two different types of modules. One is a universal learning module type that represents a cortical column in the neocortex gray matter. The working principle is modeled as Modulated Heterarchical Prediction Memory (mHPM). In mHPM, each module learns to predict a succeeding input vector given the sequence of the input vectors from lower layers and the context vectors from higher layers. The prediction is fed into the lower layers as a context signal (top-down feedback signaling), and into the higher layers as an input signal (bottom-up feedforward signaling). Rewards modulate the learning rate in those modules to memorize meaningful sequences effectively. In mHPM, each module updates in a local and distributed way compared to conventional end-to-end learning with backpropagation of the single objective loss. This local structure enables the heterarchical network of modules. The second type is an innate, special-purpose module representing various organs of the brain's subcortical system. Modules modeling organs such as the amygdala, hippocampus, and reward center are pre-programmed to enable instinctive behaviors. The hippocampus plays the role of the simulator. It is an autoregressive prediction model of the top-most level signal with a loop structure of memory, while cortical columns are lower layers that provide detailed information to the simulation. The simulation becomes the basis for learning with few trials and the deliberate planning required for operant conditioning.