To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined by the Kullback-Leibler (KL) divergence, which not only captures the notion of distance well but also yields closed-form solutions. In this paper, we consider a more general class of f-divergences and derive the corresponding policy update rules. The generic solution is expressed through the derivative of the convex conjugate function to f and includes the KL solution as a special case. Within the class of f-divergences, we further focus on a one-parameter family of {\alpha}-divergences to study effects of the choice of divergence on policy improvement. Previously known as well as new policy updates emerge for different values of {\alpha}. We show that every type of policy update comes with a compatible policy evaluation resulting from the chosen f-divergence. Interestingly, the mean-squared Bellman error minimization is closely related to policy evaluation with the Pearson $\chi^2$-divergence penalty, while the KL divergence results in the soft-max policy update and a log-sum-exp critic. We carry out asymptotic analysis of the solutions for different values of {\alpha} and demonstrate the effects of using different divergence functions on a multi-armed bandit problem and on common standard reinforcement learning problems.

The year 2017 is coming to a close, and as in years past, we look back with excitement at the medical technologies that have been gracing the pages of Medgadget. As usual, there are trends that have revealed themselves, with many research teams around the world working on similar technologies. There are also new devices that are unlike anything we've seen before, solving medical problems in novel and unexpected ways. Take a journey with us as we review the most innovative, full of impact, and revolutionary medical technologies of the past year! Ingestible devices, mostly in the form of cameras or other sensors that travel and assess the insides of the GI tract, have been around for a few years now.

The GLOBSEC NATO Adaptation Initiative, led by retired General John R. Allen, presented on Monday (27 November) its final report on the future of the Alliance. General John R. Allen is a retired United States Marine Corps four-star general, and past Deputy Commander of US Central Command, prior to serving as Commander of the International Security Assistance Force and US Forces Afghanistan (USFOR-A). Alexander Russell "Sandy" Vershbow is an American diplomat and former Deputy Secretary General of the North Atlantic Treaty Organisation. From October 2005 to October 2008, he was the United States Ambassador to South Korea. What is GLOBSEC and what is the purpose of the report? Gen. Allen: GLOBSEC is a think tank, a public policy research institute in Slovakia, headquartered in Bratislava.

By Luis Fierro Carrión (*) In March 2016, Google's AlphaGo artificial intelligence system beat Korean master Lee Sedol in the game "Go", an ancient Chinese table game. The possible moves in this game have a level of complexity much greater than those of chess. Google developed an algorithm for AlphaGo to learn recursively each time it played, through a deep neural network. AlphaGo learned to discover new strategies by itself, by playing thousands of games within its neural networks, and adjusting the connections through a process of trial and error known as "learning by reinforcement". Artificial intelligence (AI) systems have been conquering more and more complex games: tic-tac-toe in 1952, checkers in 1994, chess in 1997, "Jeopardy" (a game of questions on different subjects) in 2011; and in 2014, Google's algorithms learned how to play 49 Atari video games simply by studying the inputs in the screen pixels and the scores obtained.

More than seven out of every ten marketers are trusting just one technology to make sense of all their challenges in 2018. And it just might succeed ... if it doesn't also take their jobs. Or if privacy regulations reduce the amount of data available to power it. Artificial intelligence is set to be the most transformative technology in marketing in 2018, according to more than 345 CMOs, CEOs, and marketing experts I surveyed recently. This past year, marketers learned that they had too much data. Too much to understand, and too much data to react to.

Artificial intelligence has political, social, economic, military and even philosophical implications. And Twitter provides some good insight on them. Here are eleven key accounts that must be followed in order to understand how machines are learning to think in an increasingly complex way. Londoner Hassabis, a former chess prodigy, is one of the people in charge of DeepMind, Google's artificial intelligence platform. He is also behind AlphaZero, the software that managed to defeat the best computer chess-playing programs, after just four hours of self-learning.

THIS IS GONNA BE A OVER 40 HOUR OF CONTENT COURSE! This is Your Complete Guide to mastering statistical modelling, data visualization, machine learning and basic deep learning in R. BOOST YOUR CAREER TO THE NEXT LEVEL: This course covers ALL the aspects of practical data science, which makes this course The Only Data Science Training You Need. By the end of the course, you'll be able to store, filter, manage, and manipulate data in R to give yourself & your company a competitive edge. My name is MINERVA SINGH and I am an Oxford University MPhil (Geography and Environment) graduate. I recently finished a PhD at Cambridge University (Tropical Ecology and Conservation).

Artificial intelligence and machine learning have been shaking up many areas of business, from cybersecurity to market analytics, bots and self-driving cars. But when it comes to core corporate functions, especially those where the risks of making bad decisions are substantial, the use of artificial intelligence is still in its early stages. Take, for example, AmerisourceBergen, a drug wholesale company based in Conshohocken, Penn. The company has 19,000 employees in 47 countries, and gross revenues of $147 billion a year, good for 11th on the Fortune 500. Alexander Kugler, the company's VP of pricing, is well aware of the potential of artificial intelligence to help the company make better decisions when it sets prices for its products.

Researchers are combining Twitter, citizen science and artificial intelligence (AI) techniques to develop an early-warning system for flood-prone communities in urban areas. In a study, published in the journal Computers & Geosciences, the researchers showed how AI can be used to extract data from Twitter and crowdsourced information from mobile phone apps to build up hyper-resolution monitoring of urban flooding. "By combining social media, citizen science and artificial intelligence in urban flooding research, we hope to generate accurate predictions and provide warnings days in advance," said Roger Wang from University of Dundee in Britain. Urban flooding is difficult to monitor due to complexities in data collection and processing. This prevents detailed risk analysis, flooding control and the validation of numerical models.

The Karlovy Lazne Music Club in Prague has a new employee -- a robot DJ that gets the crowd jumping at the popular five-story nightclub, according to a report from Reuters. The robot uses software to help it select songs, scratches records, and even dances along to the beat. "Kuka," which is also the company that manufactured the robotic arm, began life as an automotive industry robot, and ended up with the record-spinner gig after the club issued a challenge to a robotics firm. Club manager Adam Lipsansky said the unique attraction draws customers in. "People are excited (about the robot), because they haven't seen anything like this around Europe, and I am not sure if there is something similar in the world," he said.