Deforestation might lead to more deadly mosquito bites. The Atlantic Forest on the eastern coast of South America is home to about 40 different mosquito species. Breakthroughs, discoveries, and DIY tips sent six days a week. If you're someone who mosquitoes just, we feel your pain. Unfortunately, new data indicates the number of mosquito species that feed on humans is increasing--and it's likely to get worse.

Ana Corina Sosa (second from left), receives the Nobel Peace Prize for her mother, Venezuelan opposition leader Maria Corina Machado, from the Chair of the Norwegian Nobel Committee Jorgen Watne Frydnes next to a photo of Machado, in Oslo on Wednesday. OSLO - Democracies must be prepared to fight for freedom in order to survive, Nobel Peace Prize laureate Maria Corina Machado said on Wednesday, in a speech delivered by her daughter during a ceremony Machado could not attend. The Venezuelan opposition leader said that the prize held profound significance, not only for her country but for the world. "It reminds the world that democracy is essential to peace," she said, via her daughter Ana Corina Sosa Machado. "And the most important, the lesson Venezuelans can share with the world, is a lesson forged on a long and difficult path: If we want democracy, we must be prepared to fight for freedom."

Options, which impose an inductive bias toward temporal and hierarchical structure, offer a powerful framework for reinforcement learning (RL). While effective in sequential decision-making, they are often handcrafted rather than learned. Among approaches for discovering options, eigenoptions have shown strong performance in exploration, but their role in credit assignment remains underexplored. In this paper, we investigate whether eigenoptions can accelerate credit assignment in model-free RL, evaluating them in tabular and pixel-based gridworlds. We find that pre-specified eigenoptions aid not only exploration but also credit assignment, whereas online discovery can bias the agent's experience too strongly and hinder learning. In the context of deep RL, we also propose a method for learning option-values under non-linear function approximation, highlighting the impact of termination conditions on performance. Our findings reveal both the promise and complexity of using eigenoptions, and options more broadly, to simultaneously support credit assignment and exploration in reinforcement learning.

Sign up for the Slatest to get the most insightful analysis, criticism, and advice out there, delivered to your inbox daily. Juan Carlos Lopez-Gomez, despite his U.S. citizenship and Social Security card, was arrested on April 16 on an unfounded suspicion of him being an "unauthorized alien." Immigration and Customs Enforcement kept him in county jail for 30 hours "based on biometric confirmation of his identity"--an obvious mistake of facial recognition technology. Another U.S. citizen, Jensy Machado, was held at gunpoint and handcuffed by ICE agents. He was another victim of mistaken identity after someone else gave his home address on a deportation order.

This work explores the creation of ambiguous images, i.e., images that may induce multistable perception, by evolutionary means. Ambiguous images are created using a general purpose approach, composed of an expression-based evolutionary engine and a set of object detectors, which are trained in advance using Machine Learning techniques. Images are evolved using Genetic Programming and object detectors are used to classify them. The information gathered during classification is used to assign fitness. In a first stage, the system is used to evolve images that resemble a single object. In a second stage, the discovery of ambiguous images is promoted by combining pairs of object detectors. The analysis of the results highlights the ability of the system to evolve ambiguous images and the differences between computational and human ambiguous images.

IT operations teams have a lot to juggle. They manage servers, networks, cloud infrastructure, user experience, application performance, and cybersecurity, often working independently of one another. Staffers are more often than not overworked, burdened with excessive alerts, and struggling to solve problems that involve multiple domains. Enter AIOps, a burgeoning field of technologies and strategies that inject artificial intelligence into IT operations in an effort to solve challenges face by IT operations teams by reducing false positives, using machine learning to spot problems before they occur, automating remediation, and seeing a holistic view of the enterprise. According to an October survey of IT leaders conducted by ZK Research and Masergy, 65% of companies are already using AIOps, and 94% say that AIOps is "important or very important" for managing network and cloud application performance.

Reasoning at multiple levels of temporal abstraction is one of the key attributes of intelligence. In reinforcement learning, this is often modeled through temporally extended courses of actions called options. Options allow agents to make predictions and to operate at different levels of abstraction within an environment. Nevertheless, approaches based on the options framework often start with the assumption that a reasonable set of options is known beforehand. When this is not the case, there are no definitive answers for which options one should consider. In this paper, we argue that the successor representation (SR), which encodes states based on the pattern of state visitation that follows them, can be seen as a natural substrate for the discovery and use of temporal abstractions. To support our claim, we take a big picture view of recent results, showing how the SR can be used to discover options that facilitate either temporally-extended exploration or planning. We cast these results as instantiations of a general framework for option discovery in which the agent's representation is used to identify useful options, which are then used to further improve its representation. This results in a virtuous, never-ending, cycle in which both the representation and the options are constantly refined based on each other. Beyond option discovery itself, we discuss how the SR allows us to augment a set of options into a combinatorially large counterpart without additional learning. This is achieved through the combination of previously learned options. Our empirical evaluation focuses on options discovered for temporally-extended exploration and on the use of the SR to combine them. The results of our experiments shed light on design decisions involved in the definition of options and demonstrate the synergy of different methods based on the SR, such as eigenoptions and the option keyboard.

I have been working with policy gradient (PG) methods for quite some time now and I thought I should continue sharing our findings here. In June, we put out a paper on how we could see PG methods from an operators perspective. I even wrote a blog post on this. Today I'm going to talk about a paper we put out last month about the role of baselines in PG methods. As in my previous post, let me first talk about the standard view of PG methods.

Researchers from North Carolina State University have developed an algorithm that could give pig farms advance notice of porcine epidemic diarrhea virus (PEDV) outbreaks. The proof-of-concept algorithm has potential for use in real-time prediction of other disease outbreaks in food animals. PEDV is a virus that causes high mortality rates in preweaned piglets. The virus emerged in the U.S. in 2013 and by 2014 had infected approximately 50 percent of breeding herds. PEDV is transmitted by contact with contaminated fecal matter.

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community, leading to some high-profile success stories such as the much publicized Deep Q-Networks (DQN). In this article we take a big picture look at how the ALE is being used by the research community. We show how diverse the evaluation methodologies in the ALE have become with time, and highlight some key concerns when evaluating agents in the ALE. We use this discussion to present some methodological best practices and provide new benchmark results using these best practices. To further the progress in the field, we introduce a new version of the ALE that supports multiple game modes and provides a form of stochasticity we call sticky actions. We conclude this big picture look by revisiting challenges posed when the ALE was introduced, summarizing the state-of-the-art in various problems and highlighting problems that remain open.