Heterogeneous knowledge naturally arises among different agents in cooperative multiagent reinforcement learning. As such, learning can be greatly improved if agents can effectively pass their knowledge on to other agents. Existing work has demonstrated that peer-to-peer knowledge transfer, a process referred to as action advising, improves team-wide learning. In contrast to previous frameworks that advise at the level of primitive actions, we aim to learn high-level teaching policies that decide when and what high-level action (e.g., sub-goal) to advise a teammate. We introduce a new learning to teach framework, called hierarchical multiagent teaching (HMAT). The proposed framework solves difficulties faced by prior work on multiagent teaching when operating in domains with long horizons, delayed rewards, and continuous states/actions by leveraging temporal abstraction and deep function approximation. Our empirical evaluations show that HMAT accelerates team-wide learning progress in difficult environments that are more complex than those explored in previous work. HMAT also learns teaching policies that can be transferred to different teammates/tasks and can even teach teammates with heterogeneous action spaces.

A video game that encourages players to rape and murder women has provoked outrage after it was listed on a popular gaming platform. Alongside sexually explicit images and a description warning of "violence, sexual assault, non-consensual sex, obscene language, necrophilia, and incest," Rape Day appeared on the Steam Store online gaming platform. Desk Plant, the game's developer, claims it is a "dark comedy" that obeys the rules of Valve, the platform's owner. We'll tell you what's true. You can form your own view.

Could a program detect potential terrorists by reading their facial expressions and behavior? This was the hypothesis put to the test by the US Transportation Security Administration (TSA) in 2003, as it began testing a new surveillance program called the Screening of Passengers by Observation Techniques program, or Spot for short. While developing the program, they consulted Paul Ekman, emeritus professor of psychology at the University of California, San Francisco. Decades earlier, Ekman had developed a method to identify minute facial expressions and map them on to corresponding emotions. This method was used to train "behavior detection officers" to scan faces for signs of deception.

Tom is an analyst at the US Department of Defense (DoD).1 All day long, he and his team collect and process massive amounts of data from a variety of sources--weather data from the National Weather Service, traffic information from the US Department of Transportation, military troop movements, public website comments, and social media posts--to assess potential threats and inform mission planning. While some of the information Tom's group collects is structured and can be categorized easily (such as tropical storms in progress or active military engagements), the vast majority is simply unstructured text, including social media conversations, comments on public websites, and narrative reports filed by field agents. Because the data is unstructured, it's difficult to find patterns and draw meaningful conclusions. Tom and his team spend much of their day poring over paper and digital documents to detect trends, patterns, and activity that could raise red flags. In response to these kinds of challenges, DoD's Defense Advanced Research Projects Agency (DARPA) recently created the Deep Exploration and Filtering of Text (DEFT) program, which uses natural language processing (NLP), a form of artificial intelligence, to automatically extract relevant information and help analysts derive actionable insights from it.2 Across government, whether in defense, transportation, human services, public safety, or health care, agencies struggle with a similar problem--making sense out of huge volumes of unstructured text to inform decisions, improve services, and save lives.

The sculpture that inspired the bizarre and horrifying "Momo" trend has been destroyed, its creator said. The statue had already rotted into an even more terrifying state than the original image, according to the Japanese artist who created it, and it was thrown away in the wake of the first round of fear about the "Momo challenge". In recent days, parents and others across the country became terrified of the so-called Momo challenge, which reports suggested involved the horrifying character – with large bulging eyes and a strange smile – contacting children and encouraging them to take part in dangerous, self-harming and even suicidal behaviour. We'll tell you what's true. You can form your own view.

Andreas Schleicher is a German data scientist--tall and precise with a grey mustache and a steely gaze. The head of the education division at the Organisation for Economic Cooperation and Development (OECD), he gives off an impression of determined focus. That's useful, considering that he's on a mission to change the way countries around the world teach their children. Society, according to Schleicher, is preparing for the future of work all wrong. We're scared that human jobs will be replaced by robots. But we're still teaching kids to think like machines. "What we know is that the kinds of things that are easy to teach, and maybe easy to test, are precisely the kinds of things that are easy to digitize and to automate," Schleicher said at the LearnIt conference in London in January. It's fairly easy to teach and test math, for example--but robots happen to be pretty good at math, too.

In 1997, David Bowie partnered with an insurance company to create Bowie bonds – a kind of asset-backed bond that gave him (and investors) a share of the current and future royalties of his music. Bowie correctly predicted that his music would only become more popular, but he didn't want to wait years into the future to reap the rewards. But maneuvers like this are pretty much only open to superstars, like Bowie. For a struggling musician hoping to break into the industry, the way that it's all set up can be a massive headache. When musicians get signed to a record label, they can get an advance on future royalties, in order to finance renting equipment or studio space, or even shooting music videos.

An autonomous rover named Zoë, designed and built by Carnegie Mellon University's Robotics Institute, drilled into the soil of Chile's Atacama Desert in 2013 and discovered unusual, highly specialized microbes. The NASA-funded mission demonstrated how robots might someday find life on Mars. The astrobiology mission was led by the Robotics Institute and the SETI Institute to test technologies for searching for life underground. The microbial analyses of the soil samples recovered by Zoë were published Feb. 28 in the journal Frontiers of Microbiology. Zoë was equipped with a one-meter drill that recovered samples several times each day.

Novelty detection is the unsupervised problem of identifying anomalies in test data which significantly differ from the training set. Novelty detection is one of the classic challenges in Machine Learning and a core component of several research areas such as fraud detection, intrusion detection, medical diagnosis, data cleaning, and fault prevention. While numerous algorithms were designed to address this problem, most methods are only suitable to model continuous numerical data. Tackling datasets composed of mixed-type features, such as numerical and categorical data, or temporal datasets describing discrete event sequences is a challenging task. In addition to the supported data types, the key criteria for efficient novelty detection methods are the ability to accurately dissociate novelties from nominal samples, the interpretability, the scalability and the robustness to anomalies located in the training data. In this thesis, we investigate novel ways to tackle these issues. In particular, we propose (i) an experimental comparison of novelty detection methods for mixed-type data (ii) an experimental comparison of novelty detection methods for sequence data, (iii) a probabilistic nonparametric novelty detection method for mixed-type data based on Dirichlet process mixtures and exponential-family distributions and (iv) an autoencoder-based novelty detection model with encoder/decoder modelled as deep Gaussian processes.

A Timed Argumentation Framework (TAF) is a formalism where arguments are only valid for consideration in a given period of time, called availability intervals, which are defined for every individual argument. The original proposal is based on a single, abstract notion of attack between arguments that remains static and permanent in time. Thus, in general, when identifying the set of acceptable arguments, the outcome associated with a TAF will vary over time. In this work we introduce an extension of TAF adding the capability of modeling a support relation between arguments. In this sense, the resulting framework provides a suitable model for different time-dependent issues. Thus, the main contribution here is to provide an enhanced framework for modeling a positive (support) and negative (attack) interaction varying over time, which are relevant in many real-world situations. This leads to a Timed Bipolar Argumentation Framework (T-BAF), where classical argument extensions can be defined. The proposal aims at advancing in the integration of temporal argumentation in different application domain.