Archive by Author

Relief Camp Manager: A Serious Game Developed Using World Health Organization’s Guidelines

3 May

A formidable paper presented as a talk at EvoGAMES 2017 in Amsterdam (The Netherlands) by Hamna Aslam.

Co-authored by: Anton Sidorov, Nikita Bogomazov, Fedor Berezyuk, Joseph Alexander Brown

ABSTRACT:

Emergency management plans rely on training in order to provide support to first responders, government planners, and affected persons in potential disaster zone. Serious Games have proved to be useful in capturing and invoking people’s attention and emergency management education is also being delivered through games. The paper presents a relief camp game developed using the figures from World Health Organization’s (WHO) report on water, sanitation and hygiene guidelines in emergencies. The game play provides player an understanding of the management of relief camps by giving them a supervisory role to design and organize camp areas. It also encourages players to introduce their own ideas in setting up relief camps. The player is competing against evolutionary computation algorithm. The aims are to create awareness about relief camp management strategies and improving the present approaches for better plans via human competitive testing.

PRESENTATION:

https://www.researchgate.net/project/Relief-Camp-Manager-A-Serious-Game-Developed-Using-World-Health-Organizations-Guidelines

LINK TO THE PAPER:

https://link.springer.com/chapter/10.1007/978-3-319-55849-3_27

https://www.researchgate.net/profile/Joseph_Brown7/publication/313164852_Relief_Camp_Manager_A_Serious_Game_using_the_World_Health_Organization’s_Relief_Camp_Guidelines/links/5891d79d458515aeac941e9f/Relief-Camp-Manager-A-Serious-Game-using-the-World-Health-Organizations-Relief-Camp-Guidelines.pdf

Evolving Game-specific UCB Alternatives for General Video Game Playing

3 May

Interesting paper presented as a talk at EvoGAMES 2017 in Amsterdam (The Netherlands) by Ivan Bravi.

Co-authored by: Ahmed Khalifa , Christoffer Holmgard , Julian Togelius

ABSTRACT:

At the core of the most popular version of the Monte Carlo Tree Search (MCTS) algorithm is the UCB1 (Upper Confidence Bound) equation. This equation decides which node to explore next, and therefore shapes the behavior of the search process. If the UCB1 equation is replaced with another equation, the behavior of the MCTS algorithm changes, which might increase its performance on certain problems (and decrease it on others). In this paper, we use genetic programming to evolve replacements to the UCB1 equation targeted at playing individual games in the General Video Game AI (GVGAI) Framework. Each equation is evolved to maximize playing strength in a single game, but is then also tested on all other games in our test set. For every game included in the experiments, we found a UCB replacement that performs significantly better than standard UCB1. Additionally, evolved UCB replacements also tend to improve performance in some GVGAI games for which they are not evolved, showing that improvements generalize across games to clusters of games with similar game mechanics or algorithmic performance. Such an evolved portfolio of UCB variations could be useful for a hyper-heuristic game-playing agent, allowing it to select the most appropriate heuristics for particular games or problems in general.

PRESENTATION:

Ivan Bravi – EvoGAMES – Evolving UCT alternatives

LINK TO THE PAPER:

https://link.springer.com/chapter/10.1007/978-3-319-55849-3_26

http://julian.togelius.com/Bravi2017Evolving.pdf