Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training dataset and prone to missing rewarding actions. For training more effective agents, we propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. We further propose a simple modification to the classical policy-matching methods for regularizing with respect to the dual form of the Jensen--Shannon divergence and the integral probability metrics. We theoretically show the correctness of the policy-matching approach, and the correctness and a good finite-sample property of our modification. An effective instantiation of our framework through the GAN structure is provided, together with techniques to explicitly smooth the state-action mapping for robust generalization beyond the static dataset. Extensive experiments and ablation study on the D4RL benchmark validate our framework and the effectiveness of our algorithmic designs.

Previous research has shown that the fairness and the legitimacy of a moral decision-maker are important for people's acceptance of and compliance with the decision-maker. As technology rapidly advances, there have been increasing hopes and concerns about building artificially intelligent entities that are designed to intervene against norm violations. However, it is unclear how people would perceive artificial moral regulators that impose punishment on human wrongdoers. Grounded in theories of psychology and law, we predict that the perceived fairness of punishment imposed by a robot would increase the legitimacy of the robot functioning as a moral regulator, which would in turn, increase people's willingness to accept and comply with the robot's decisions. We close with a conceptual framework for building a robot moral regulator that successfully can regulate norm violations.

The most prominent tasks in emotion analysis are to assign emotions to texts and to understand how emotions manifest in language. An observation for NLP is that emotions can be communicated implicitly by referring to events, appealing to an empathetic, intersubjective understanding of events, even without explicitly mentioning an emotion name. In psychology, the class of emotion theories known as appraisal theories aims at explaining the link between events and emotions. Appraisals can be formalized as variables that measure a cognitive evaluation by people living through an event that they consider relevant. They include the assessment if an event is novel, if the person considers themselves to be responsible, if it is in line with the own goals, and many others. Such appraisals explain which emotions are developed based on an event, e.g., that a novel situation can induce surprise or one with uncertain consequences could evoke fear. We analyze the suitability of appraisal theories for emotion analysis in text with the goal of understanding if appraisal concepts can reliably be reconstructed by annotators, if they can be predicted by text classifiers, and if appraisal concepts help to identify emotion categories. To achieve that, we compile a corpus by asking people to textually describe events that triggered particular emotions and to disclose their appraisals. Then, we ask readers to reconstruct emotions and appraisals from the text. This setup allows us to measure if emotions and appraisals can be recovered purely from text and provides a human baseline. Our comparison of text classification methods to human annotators shows that both can reliably detect emotions and appraisals with similar performance. Therefore, appraisals constitute an alternative computational emotion analysis paradigm and further improve the categorization of emotions in text with joint models.

An MQ-28 Ghost Bat drone flies in tests for the Royal Australian Air Force. WASHINGTON -- The US Air Force is set to begin flight experiments with Boeing's MQ-28 Ghost Bat, a combat drone developed for the Australian air force that may help its American counterpart learn how to operate unmanned aircraft alongside fighter jets. Lt. Gen. Clint Hinote, who leads Air Force Futures, told Breaking Defense in a September 20 interview that the service is "getting ready to take delivery" of a drone prototype through the Pentagon's research and engineering office, also known as OSD (R&E). "It might look a lot like an Australian thing," he joked, referring to the Ghost Bat, which first flew in 2021 at Royal Australian Air Force Base Woomera. Pentagon spokesman Lt. Cdr. Tim Gorman confirmed that the research and engineering office is involved in development and experimentation efforts involving Ghost Bat, saying that "OSD (R&E) continually works with the services to validate technologies that are key to advancing and fielding next generation capabilities."

Robotics company Boston Dynamics is pledging not to support the weaponization of its products and calling for its competitors to do the same. In a new letter, the firm said recent efforts to weaponize their robots - such as a Russian inventor who strapped a submachine gun to a Unitree robot and filmed it shooting targets - had added to the urgency of their declaration. 'We pledge that we will not weaponize our advanced-mobility general-purpose robots or the software we develop that enables advanced robotics and we will not support others to do so,' the letter, which was signed by six other companies, including Unitree, states. The Massachusetts-based tech company has frequently seen videos of its robot dogs Spot or its humanoid robot Atlas go viral for performing various stunts or athletic tasks in public. Anyone who has watched the Black Mirror episode'Metalhead' that features a robotic dog or seen the film Angel Has Fallen, which features an attempted assassination of the president by autonomous, AI-powered drones, is aware of the potential risks these new technologies pose.

CURT NICKISCH: Welcome to the HBR IdeaCast from Harvard Business Review. A shiny new piece of technology is not good enough on its own. It needs to be implemented at the right time, used in the right context, and accepted in the right culture, applied in the right way. In short, it needs to be part of the right system. AI can help individuals and teams make better predictions, combine that with judgment and you get better decisions. But those decisions have ripple effects on other parts of the system, ripple effects that can undermine the very prediction that was made. Our guest today says, "If organizations want to take artificial intelligence to the next level, they need to get better at coordinating optimal decisions over a wider network."

In this paper, we present InferES - an original corpus for Natural Language Inference (NLI) in European Spanish. We propose, implement, and analyze a variety of corpus-creating strategies utilizing expert linguists and crowd workers. The objectives behind InferES are to provide high-quality data, and, at the same time to facilitate the systematic evaluation of automated systems. Specifically, we focus on measuring and improving the performance of machine learning systems on negation-based adversarial examples and their ability to generalize across out-of-distribution topics. We train two transformer models on InferES (8,055 gold examples) in a variety of scenarios. Our best model obtains 72.8% accuracy, leaving a lot of room for improvement. The "hypothesis-only" baseline performs only 2%-5% higher than majority, indicating much fewer annotation artifacts than prior work. We find that models trained on InferES generalize very well across topics (both in- and out-of-distribution) and perform moderately well on negation-based adversarial examples.

We evaluate the reasoning abilities of large language models in multilingual settings. We introduce the Multilingual Grade School Math (MGSM) benchmark, by manually translating 250 grade-school math problems from the GSM8K dataset (Cobbe et al., 2021) into ten typologically diverse languages. We find that the ability to solve MGSM problems via chain-of-thought prompting emerges with increasing model scale, and that models have strikingly strong multilingual reasoning abilities, even in underrepresented languages such as Bengali and Swahili. Finally, we show that the multilingual reasoning abilities of language models extend to other tasks such as commonsense reasoning and word-in-context semantic judgment. The MGSM benchmark is publicly available at https://github.com/google-research/url-nlp.

Hyperbox-based machine learning algorithms are an important and popular branch of machine learning in the construction of classifiers using fuzzy sets and logic theory and neural network architectures. This type of learning is characterised by many strong points of modern predictors such as a high scalability, explainability, online adaptation, effective learning from a small amount of data, native ability to deal with missing data and accommodating new classes. Nevertheless, there is no comprehensive existing package for hyperbox-based machine learning which can serve as a benchmark for research and allow non-expert users to apply these algorithms easily. hyperbox-brain is an open-source Python library implementing the leading hyperbox-based machine learning algorithms. This library exposes a unified API which closely follows and is compatible with the renowned scikit-learn and numpy toolboxes. The library may be installed from Python Package Index (PyPI) and the conda package manager and is distributed under the GPL-3 license. The source code, documentation, detailed tutorials, and the full descriptions of the API are available at https://uts-caslab.github.io/hyperbox-brain.

Speech is the fundamental mode of human communication, and its synthesis has long been a core priority in human-computer interaction research. In recent years, machines have managed to master the art of generating speech that is understandable by humans. But the linguistic content of an utterance encompasses only a part of its meaning. Affect, or expressivity, has the capacity to turn speech into a medium capable of conveying intimate thoughts, feelings, and emotions -- aspects that are essential for engaging and naturalistic interpersonal communication. While the goal of imparting expressivity to synthesised utterances has so far remained elusive, following recent advances in text-to-speech synthesis, a paradigm shift is well under way in the fields of affective speech synthesis and conversion as well. Deep learning, as the technology which underlies most of the recent advances in artificial intelligence, is spearheading these efforts. In the present overview, we outline ongoing trends and summarise state-of-the-art approaches in an attempt to provide a comprehensive overview of this exciting field.