Conducting randomized experiments in education settings raises the question of how we can use machine learning techniques to improve educational interventions. Using Multi-Armed Bandits (MAB) algorithms like Thompson Sampling (TS) in adaptive experiments can increase students' chances of obtaining better outcomes by increasing the probability of assignment to the most optimal condition (arm), even before an intervention completes. This is an advantage over traditional A/B testing, which may allocate an equal number of students to both optimal and non-optimal conditions. The problem is the exploration-exploitation trade-off. Even though adaptive policies aim to collect enough information to allocate more students to better arms reliably, past work shows that this may not be enough exploration to draw reliable conclusions about whether arms differ. Hence, it is of interest to provide additional uniform random (UR) exploration throughout the experiment. This paper shows a real-world adaptive experiment on how students engage with instructors' weekly email reminders to build their time management habits. Our metric of interest is open email rates which tracks the arms represented by different subject lines. These are delivered following different allocation algorithms: UR, TS, and what we identified as TS{\dag} - which combines both TS and UR rewards to update its priors. We highlight problems with these adaptive algorithms - such as possible exploitation of an arm when there is no significant difference - and address their causes and consequences. Future directions includes studying situations where the early choice of the optimal arm is not ideal and how adaptive algorithms can address them.

Shane Rafferty plays video games for a living. He's neither a developer nor a ranked professional, but his work revolves around gaming all the same: Rafferty is a gaming technology specialist. As the name suggests, he uses technology--and video games in particular--to provide social and emotional support for hospitalized children and their families. Though the job description sounds like fantasy, gaming technology specialists are a reality at more than 50 hospitals worldwide. Among them is the Ann & Robert H. Lurie Children's Hospital of Chicago.

This survey article has grown out of the RL4ED workshop organized by the authors at the Educational Data Mining (EDM) 2021 conference. We organized this workshop as part of a community-building effort to bring together researchers and practitioners interested in the broad areas of reinforcement learning (RL) and education (ED). This article aims to provide an overview of the workshop activities and summarize the main research directions in the area of RL for ED.

Fox Business Flash top headlines are here. Check out what's clicking on FoxBusiness.com. U.S. Army war planners believe winning a major power war against Russia or China would require an intricate and sophisticated blend of weapons, effects, networking and tactics, creating a need for the service to revamp its traditional Combined Arms Maneuver warfare approach. Traditional Combined Arms Maneuver requires a sophisticated mix of integrated attack strategies, including armored vehicles, artillery, air assets such as helicopters, infantry and long-range rockets. Based upon a specific and carefully analyzed understanding of the battlespace, Combined Arms Maneuver strategy seeks to attack in a highly coordinated way, something that senior Army officials often describe as almost like a symphony.

When a precision-guided artillery projectile exploded an enemy target from 64km (39.8 miles) away in the Arizona desert during a recent live-fire exercise, the Army took a new step toward redefining land-attack tactics and paving the way toward a new warfare era in long-range fires. In a March 2020 demonstration firing of the emerging Long Range Precision Fires program at Yuma Proving Grounds, Ariz., an Army Howitzer blasted an Excalibur 155m artillery round out to ranges twice that of what existing artillery weapons are now capable of. The new weapon in development, called Extended Range Cannon Artillery, not only preserves the GPS-guided precision attack options characteristic of present-day artillery, but also extends attack ranges from roughly 30km (18.6 miles) out to nearly 70km (43.5 miles). This, senior Army weapons developers explain, gives ground artillery commanders the ability to destroy previously unreachable air and ground targets. "This provides a longer range capability, enabling commanders to attack helicopters, UAVs and go after other new targets farther range," Gen.

See how self-driving cars prepare for the real world inside a private testing facility owned by Google's autonomous car company, Waymo. The Navya passenger shuttle is among myriad autonomous vehicles worldwide in various stages of development. And at an event Nov. 17 and 18 on the University of Wisconsin Madison College of Engineering campus, visitors will have the opportunity to check it out. The Taiwan-based electronic manufacturer's plans to use driverless vehicles to move thousands of workers a day at its 22 million-square-foot campus about 30 miles south of Milwaukee could pave new ground for the technology, which promises to reshape transportation in this country. More than a dozen states are scrambling to get ready for self-driving cars, and while major companies from Google to General Motors are testing such cars, few are in use yet.

MADISON, WISCONSIN – Most cars on Wisconsin roads will be driverless two decades from now, a University of Wisconsin researcher says. "They're coming, whether we like it or not," engineering professor David Noyce said at an Assembly committee hearing on the future of autonomous cars Wednesday. Driverless cars can make driving safer, cut traffic, reduce emissions and give more people the ability to get around, according to Noyce and others who testified. But many challenges remain: bad weather and hackers can throw off the technology, the cars are pricey and legal questions remain, such as who is liable when something goes wrong. Last month, the University of Wisconsin-Madison Traffic Operations and Safety Laboratory was one of 10 groups nationwide the federal government designated to test the vehicles.