In this paper, we study the problem of obtaining a control policy that can mimic and then outperform expert demonstrations in Markov decision processes where the reward function is unknown to the learning agent. One main relevant approach is the inverse reinforcement learning (IRL), which mainly focuses on inferring a reward function from expert demonstrations. The obtained control policy by IRL and the associated algorithms, however, can hardly outperform expert demonstrations. To overcome this limitation, we propose a novel method that enables the learning agent to outperform the demonstrator via a new concurrent reward and action policy learning approach. In particular, we first propose a new stereo utility definition that aims to address the bias in the interpretation of expert demonstrations. We then propose a loss function for the learning agent to learn reward and action policies concurrently such that the learning agent can outperform expert demonstrations. The performance of the proposed method is first demonstrated in OpenAI environments. Further efforts are conducted to experimentally validate the proposed method via an indoor drone flight scenario.

A cellular-connected unmanned aerial vehicle (UAV)faces several key challenges concerning connectivity and energy efficiency. Through a learning-based strategy, we propose a general novel multi-armed bandit (MAB) algorithm to reduce disconnectivity time, handover rate, and energy consumption of UAV by taking into account its time of task completion. By formulating the problem as a function of UAV's velocity, we show how each of these performance indicators (PIs) is improved by adopting a proper range of corresponding learning parameter, e.g. 50% reduction in HO rate as compared to a blind strategy. However, results reveal that the optimal combination of the learning parameters depends critically on any specific application and the weights of PIs on the final objective function.

The E.U. supports the Iranian nuclear deal as the Trump administration announces new sanctions. Iran's Revolutionary Guard on Saturday threatened to avenge the killing of its top general, saying it would go after everyone responsible for the January U.S. drone strike in Iraq. The guard's website quoted Gen. Hossein Salami as saying, "Mr. Our revenge for martyrdom of our great general is obvious, serious and real." FILE: Chief of Iran's Revolutionary Guard Gen. Hossein Salami speaks at a pro-government rally, in Tehran, Iran.

The chief of Iran's paramilitary Revolutionary Guard threatened Saturday to go after everyone who had a role in a top general's January killing during a U.S. drone strike in Iraq. The guard's website quoted Gen. Hossein Salami as saying, "Mr. Our revenge for martyrdom of our great general is obvious, serious and real." U.S. President Donald Trump warned this week that Washington would harshly respond to any Iranian attempts to take revenge for the death of Gen. Qassem Soleimani, tweeting that "if they hit us in any way, any form, written instructions already done we're going to hit them 1000 times harder." The president's warning came in response to a report that Iran was plotting to assassinate the U.S. ambassador to South Africa in retaliation for Soleimani's killing at Baghdad's airport at the beginning of the year.

Artificial intelligence is the bleeding-edge technology that can contribute and enhance the ways of living tremendously.

The White House's recent decision to allow the sale of advanced weapons systems to the United Arab Emirates highlights the deliberate shift in US policy towards the UAE after it signed "normalisation" accords with Israel. Why would the UAE want American drones as it already has dozens of Chinese armed unmanned aerial vehicles (UAVs) in its inventory? And why has the United States now agreed to these sales, overcoming its traditional reticence to sell sophisticated weapons to other countries? Chinese armed drones have made a significant effect on the battlefields across the Middle East and North Africa. They have been used to assassinate Houthi rebel leaders in Yemen, kill ISIL-affiliated fighters in the Sinai, and for a time help Khalifa Haftar dominate the battlespace in Libya.

Here we discuss the five technology megatrends of our times and how their adoption was accelerated by the reality of trying to sustain business as well as live and cope in a COVID-19-impacted world. While many were juggling at-home schooling of children and professional responsibilities amid stay-at-home orders because of COVID-19, the digital transformation accelerated. Here are five of the biggest technology trends of our times and how the coronavirus pandemic accelerated their adoption. This acceleration will change how businesses operate and compete as they emerge out of the pandemic.

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.

New drone video captured the mess Hurricane Sally left behind on Alabama's coastline after tearing through early Wednesday morning with 105 mph winds, torrential rainfall and a powerful storm surge. The storm tore apart buildings, hurled boats and debris around, and dumped as much as 30 inches of rain in southern Alabama and the Florida Panhandle before downgrading to a tropical storm Wednesday. It continued to weaken to a post-tropical depression Thursday as it moved northeast. The wall of a residential high-rise building was sheared completely off in the storm, leaving multiple levels exposed, the video shows. Sally tore through bedrooms and furniture, leaving dresser drawers open and bedding unraveled, the video shows.

We show that automated person detection under occlusion conditions can be significantly improved by combining multi-perspective images before classification. Here, we employed image integration by Airborne Optical Sectioning (AOS)---a synthetic aperture imaging technique that uses camera drones to capture unstructured thermal light fields---to achieve this with a precision/recall of 96/93%. Finding lost or injured people in dense forests is not generally feasible with thermal recordings, but becomes practical with use of AOS integral images. Our findings lay the foundation for effective future search and rescue technologies that can be applied in combination with autonomous or manned aircraft. They can also be beneficial for other fields that currently suffer from inaccurate classification of partially occluded people, animals, or objects.