Search

Constructing strong AI systems for video games is difficult due to enormous state and action spaces and the lack of good state evaluation functions and high-level action abstractions. In spite of recent research progress in popular video game genres such as Atari 2600 console games and multiplayer online battle arena (MOBA) games, to this day strong human players can still defeat the best AI systems in adversarial video games. In this paper, we propose to use a deep Convolutional Neural Network (CNN) to select among a limited set of abstract action choices in Real-Time Strategy (RTS) games, and to utilize the remaining computation time for game tree search to improve low-level tactics. The CNN is trained by supervised learning on game states labeled by Puppet Search, a strategic search algorithm that uses action abstractions. Replacing Puppet Search by a CNN frees up time that can be used for improving units? tactical behavior while executing the strategic plan. Experiments in the mRTS game show that the combined algorithm results in higher win-rates than either of its two independent components and other state-of-the-art mRTS agents. We then present a case-study that investigates how deep Reinforcement Learning (RL) can be used in modern video games, such as Total War: Warhammer, to improve tactical multi-agent AI modules. We use popular RL algorithms such as Deep-Q Networks (DQN) and Asynchronous Advantage-Actor Critic (A3C), basic network architectures and minimal hyper-parameter tuning to learn complex cooperative behaviors that defeat the highest difficulty built-in AI in mediumscale scenarios.

Videogames are nowadays one of the biggest entertainment industries in the world. Being part of this industry means competing against lots of other companies and developers, thus, making fanbases of vital importance. They are a group of clients that constantly support your company because your video games are fun. Videogames are most entertaining when the difficulty level is a good match for the player's skill, increasing the player engagement. However, not all players are equally proficient, so some kind of difficulty selection is required. In this paper, we will present Dynamic Difficulty Adjustment (DDA), a recently arising research topic, which aims to develop an automated difficulty selection mechanism that keeps the player engaged and properly challenged, neither bored nor overwhelmed. We will present some recent research addressing this issue, as well as an overview of how to implement it. Satisfactorily solving the DDA problem directly affects the player's experience when playing the game, making it of high interest to any game developer, from independent ones, to 100 billion dollar businesses, because of the potential impacts in player retention and monetization.

BACKGROUND Advances in the development of information and communication technologies have facilitated social and sexual interrelationships, thanks to the websites and apps created to this end. However, these resources can also encourage sexual contacts without appropriate preventive measures in relation to HIV and other sexually transmitted infections (STIs). How can users be helped to benefit from the advantages of these apps while keeping in mind those preventive measures? OBJECTIVE This study aimed to prevent STIs by helping users to remember preventive measures in the risky situations. METHODS We have used the design and creation methodology and have developed a software system. This system has two parts: an Android operating system app with emphasis on ubiquitous computing and gamification as well as a server with a webpage. First, a functional test with 5 men who have sex with men (MSM) allowed us to test the app with end users. In addition, a feasibility test with 4 MSM for a month allowed us to try the UBESAFE system with all its functionalities. RESULTS The main output is a system called UBESAFE that is addressed to MSM. The system has two main parts: (1) an app that sends preventive contextualized messages to users when they use a contact app or when they are near a point where sexual contacts are likely and (2) a server part that was managed by the public health agency of Barcelona (ASPB), which preserves the quality and pertinence of messages and places and offers instant help to users. To increase users’ adherence, UBESAFE uses a gamified system to engage users in the creation of preventive messages. Users increased the initial pool of messages by more than 100% (34/30) and created more than 56% (9/16) of places (named hot zones). CONCLUSIONS The system helped MSM who used it to become conscious about HIV and other STIs. The system also helped the ASPB to stay in contact with MSM and to detect behaviors that could benefit from preventive measures. All functions were performed in a nonintrusive manner because users used the app privately. Furthermore, the system has shown how important it is to make users a part of the creation process as well as to develop apps that work by themselves and thus become useful to the users.

Background Advances in the development of information and communication technologies have facilitated social and sexual interrelationships, thanks to the websites and apps created to this end. However, these resources can also encourage sexual contacts without appropriate preventive measures in relation to HIV and other sexually transmitted infections (STIs). How can users be helped to benefit from the advantages of these apps while keeping in mind those preventive measures? Objective This study aimed to prevent STIs by helping users to remember preventive measures in the risky situations. Methods We have used the design and creation methodology and have developed a software system. This system has two parts: an Android operating system app with emphasis on ubiquitous computing and gamification as well as a server with a webpage. First, a functional test with 5 men who have sex with men (MSM) allowed us to test the app with end users. In addition, a feasibility test with 4 MSM for a month allowed us to try the UBESAFE system with all its functionalities. Results The main output is a system called UBESAFE that is addressed to MSM. The system has two main parts: (1) an app that sends preventive contextualized messages to users when they use a contact app or when they are near a point where sexual contacts are likely and (2) a server part that was managed by the public health agency of Barcelona (ASPB), which preserves the quality and pertinence of messages and places and offers instant help to users. To increase users’ adherence, UBESAFE uses a gamified system to engage users in the creation of preventive messages. Users increased the initial pool of messages by more than 100% (34/30) and created more than 56% (9/16) of places (named hot zones). Conclusions The system helped MSM who used it to become conscious about HIV and other STIs. The system also helped the ASPB to stay in contact with MSM and to detect behaviors that could benefit from preventive measures. All functions were performed in a nonintrusive manner because users used the app privately. Furthermore, the system has shown how important it is to make users a part of the creation process as well as to develop apps that work by themselves and thus become useful to the users.

This article presents the results of the first edition of the microRTS (μRTS) AI competition, which was hosted by the IEEE Computational Intelligence in Games (CIG) 2017 conference. The goal of the competition is to spur research on AI techniques for real-time strategy (RTS) games. In this first edition, the competition received three submissions, focusing on address- ing problems such as balancing long-term and short-term search, the use of machine learning to learn how to play against certain opponents, and finally, dealing with partial observability in RTS games.

Real-time strategy (RTS) games, such as Blizzard's StarCraft, are fast paced war simulation games in which players have to manage economies, control many dozens of units, and deal with uncertainty about opposing unit locations in real-time. Even in perfect information settings, constructing strong AI systems has been difficult due to enormous state and action spaces and the lack of good state evaluation functions and high-level action abstractions. To this day, good human players are still handily defeating the best RTS game AI systems, but this may change in the near future given the recent success of deep convolutional neural networks (CNNs) in computer Go, which demonstrated how networks can be used for evaluating complex game states accurately and to focus look-ahead search. In this paper we present a CNN for RTS game state evaluation that goes beyond commonly used material based evaluations by also taking spatial relations between units into account. We evaluate the CNN's performance by comparing it with various other evaluation functions by means of tournaments played by several state-of-the-art search algorithms. We find that, despite its much slower evaluation speed, on average the CNN based search performs significantly better compared to simpler but faster evaluations. These promising initial results together with recent advances in hierarchical search suggest that dominating human players in RTS games may not be far off.

The Gemini Planet Imager is a next-generation instrument for the direct detection and characterization of young warm exoplanets, designed to be an order of magnitude more sensitive than existing facilities. It combines a 1700-actuator adaptive optics system, an apodized-pupil Lyot coronagraph, a precision interferometric infrared wavefront sensor, and a integral field spectrograph. All hardware and software subsystems are now complete and undergoing integration and test at UC Santa Cruz. We will present test results on each subsystem and the results of end-to-end testing. In laboratory testing, GPI has achieved a raw contrast (without post-processing) of 10-6 5σ at 0.4”, and with multiwavelength speckle suppression, 2x10-7 at the same separation.

Starting 2009, the ALMA project initiated one of its most exciting phases within construction: the first antenna from one of the vendors was delivered to the Assembly, Integration and Verification team. With this milestone and the closure of the ALMA Test Facility in New Mexico, the JAO Computing Group in Chile found itself in the front line of the project's software deployment and integration effort. Among the group's main responsibilities are the deployment, configuration and support of the observation systems, in addition to infrastructure administration, all of which needs to be done in close coordination with the development groups in Europe, North America and Japan. Software support has been the primary interaction key with the current users (mainly scientists, operators and hardware engineers), as the software is normally the most visible part of the system. During this first year of work with the production hardware, three consecutive software releases have been deployed and commissioned. Also, the first three antennas have been moved to the Array Operations Site, at 5.000 meters elevation, and the complete end-to-end system has been successfully tested. This paper shares the experience of this 15-people group as part of the construction team at the ALMA site, and working together with Computing IPT, on the achievements and problems overcomed during this period. It explores the excellent results of teamwork, and also some of the troubles that such a complex and geographically distributed project can run into. Finally, it approaches the challenges still to come, with the transition to the ALMA operations plan.

The Atacama Large Millimeter Array (ALMA) is a joint project between astronomical organizations in Europe, North America, and Japan. ALMA will consist of at least 50 twelve meter antennas operating in the millimeter and submillimeter wavelength range. It will be located at an altitude above 5000m in the Chilean Atacama desert. The ALMA Test Facility (ATF), located in New Mexico, USA, is a proving ground for development and testing of hardware, software, commissioning and operational procedure. At the ATF emphasis has shifted from hardware testing to software and operational functionality. The support of the varied goals of the ATF requires stable control software and at the same time flexibility for integrating newly developed features. For this purpose regression testing has been introduced in the form of a semi-automated procedure. This supplements the established offline testing and focuses on operational functionality as well as verifying that previously fixed faults did not re-emerge. The regression tests are carried out on a weekly basis as a compromise between the developers' response- and the available technical time. The frequent feedback allows the validation of submitted fixes and the prompt detection of sideeffects and reappearing issues. Results of nine months are presented that show the evolution of test outcomes, supporting the conclusion that the regression testing helped to improve the speed of convergence towards stable releases at the ATF. They also provided an opportunity to validate newly developed or re-factored software at an early stage at the test facility, supporting its eventual integration. Hopefully this regression test procedure will be adapted to commissioning operations in Chile.