The growing demand for robots able to act autonomously in complex scenarios has widely accelerated the introduction of Reinforcement Learning (RL) in robots control applications. However, the trial and error intrinsic nature of RL may result in long training time on real robots and, moreover, it may lead to dangerous outcomes. While simulators are useful tools to accelerate RL training and to ensure safety, they often are provided only with an approximated model of robot dynamics and of its interaction with the surrounding environment, thus resulting in what is called the reality gap (RG): a mismatch of simulated and real control-law performances caused by the inaccurate representation of the real environment in simulation. The most undesirable result occurs when the controller learnt in simulation fails the task on the real robot, thus resulting in an unsuccessful sim-to-real transfer. The goal of the present survey is threefold: (1) to identify the main approaches to face the RG problem in the context of robot control with RL, (2) to point out their shortcomings, and (3) to outline new potential research areas.

A large class of entity extraction tasks from text that is either semistructured or fully unstructured may be addressed by regular expressions, because in many practical cases the relevant entities follow an underlying syntactical pattern and this pattern may be described by a regular expression. In this work, we consider the long-standing problem of synthesizing such expressions automatically, based solely on examples of the desired behavior. We present the design and implementation of a system capable of addressing extraction tasks of realistic complexity. Our system is based on an evolutionary procedure carefully tailored to the specific needs of regular expression generation by examples. The procedure executes a search driven by a multiobjective optimization strategy aimed at simultaneously improving multiple performance indexes of candidate solutions while at the same time ensuring an adequate exploration of the huge solution space. We assess our proposal experimentally in great depth, on a number of challenging datasets. The accuracy of the obtained solutions seems to be adequate for practical usage and improves over earlier proposals significantly. Most importantly, our results are highly competitive even with respect to human operators. A prototype is available as a web application at <;uri xlink:type="simple">http://regex.inginf.units.it<;/uri>.

The increasing diffusion of smart devices, along with the dynamism of the mobile applications ecosystem, are boosting the production of malware for the Android platform. So far, many different methods have been developed for detecting Android malware, based on either static or dynamic analysis. The main limitations of existing methods include: low accuracy, proneness to evasion techniques, and weak validation, often limited to emulators or modified kernels. We propose an Android malware detection method, based on sequences of system calls, that overcomes these limitations. The assumption is that malicious behaviors (e.g., sending high premium rate SMS, cyphering data for ransom, botnet capabilities, and so on) are implemented by specific system calls sequences: yet, no apriori knowledge is available about which sequences are associated with which malicious behaviors, in particular in the mobile applications ecosystem where new malware and non-malware applications continuously arise. Hence, we use Machine Learning to automatically learn these associations (a sort of "fingerprint" of the malware); then we exploit them to actually detect malware. Experimentation on 20000 execution traces of 2000 applications (1000 of them being malware belonging to different malware families), performed on a real device, shows promising results: we obtain a detection accuracy of 97%. Moreover, we show that the proposed method can cope with the dynamism of the mobile apps ecosystem, since it can detect unknown malware

With the wide diffusion of smartphones and their usage in a plethora of processes and activities, these devices have been handling an increasing variety of sensitive resources. Attackers are hence producing a large number of malware applications for Android (the most spread mobile platform), often by slightly modifying existing applications, which results in malware being organized in families. Some works in the literature showed that opcodes are informative for detecting malware, not only in the Android platform. In this paper, we investigate if frequencies of ngrams of opcodes are effective in detecting Android malware and if there is some significant malware family for which they are more or less effective. To this end, we designed a method based on state-of-the-art classifiers applied to frequencies of opcodes ngrams. Then, we experimentally evaluated it on a recent dataset composed of 11120 applications, 5560 of which are malware belonging to several different families. Results show that an accuracy of 97% can be obtained on the average, whereas perfect detection rate is achieved for more than one malware family.