References of "Safadi, Firas"
     in
Bookmark and Share    
Full Text
See detailArtificial Intelligence in Video Games: Towards a Unified Framework
Safadi, Firas ULg

Doctoral thesis (2015)

The work presented in this dissertation revolves around the problem of designing artificial intelligence (AI) for video games. This problem becomes increasingly challenging as video games grow in ... [more ▼]

The work presented in this dissertation revolves around the problem of designing artificial intelligence (AI) for video games. This problem becomes increasingly challenging as video games grow in complexity. With modern video games frequently featuring sophisticated and realistic environments, the need for smart and comprehensive agents that understand the various aspects of these environments is pressing. Although machine learning techniques are being successfully applied in a multitude of domains to solve AI problems, they are not yet ready to enable the creation of fully autonomous agent that can reliably learn to understand the environments found in complex video games. Since video game AI is often specifically designed for each game, video game AI tools currently focus on allowing video game developers to quickly and efficiently create specific AI. One issue with this approach is that it does not efficiently exploit the numerous similarities that exist between video games not only of the same genre, but of different genres too, resulting in a difficulty to handle the many aspects of a complex and realistic environment independently for each video game. These similarities, however, exist on a conceptual level. While video games do indeed share a variety of concepts, their interpretations vary from one game to another. Hence, these similarities can only be directly exploited at a conceptual level. Inspired by the human ability to detect analogies between games and apply similar behavior on a conceptual level, this thesis suggests an approach based on the use of a unified conceptual framework to enable the development of conceptual AI which relies on conceptual views and actions to define basic yet reasonable and robust behavior. Because conceptual AI is not tied to any game in particular, it benefits from a continuous development process as opposed to a development that is confined to the scope of a single game project. [less ▲]

Detailed reference viewed: 55 (9 ULg)
Full Text
Peer Reviewed
See detailArtificial Intelligence in Video Games: Towards a Unified Framework
Safadi, Firas ULg; Fonteneau, Raphaël ULg; Ernst, Damien ULg

in International Journal of Computer Games Technology (2015), 2015

With modern video games frequently featuring sophisticated and realistic environments, the need for smart and comprehensive agents that understand the various aspects of complex environments is pressing ... [more ▼]

With modern video games frequently featuring sophisticated and realistic environments, the need for smart and comprehensive agents that understand the various aspects of complex environments is pressing. Since video game AI is often specifically designed for each game, video game AI tools currently focus on allowing video game developers to quickly and efficiently create specific AI. One issue with this approach is that it does not efficiently exploit the numerous similarities that exist between video games not only of the same genre, but of different genres too, resulting in a difficulty to handle the many aspects of a complex environment independently for each video game. Inspired by the human ability to detect analogies between games and apply similar behavior on a conceptual level, this paper suggests an approach based on the use of a unified conceptual framework to enable the development of conceptual AI which relies on conceptual views and actions to define basic yet reasonable and robust behavior. The approach is illustrated using two video games, Raven and StarCraft: Brood War. [less ▲]

Detailed reference viewed: 346 (30 ULg)
Full Text
Peer Reviewed
See detailImitative Learning for Real-Time Strategy Games
Gemine, Quentin ULg; Safadi, Firas ULg; Fonteneau, Raphaël ULg et al

in Proceedings of the 2012 IEEE Conference on Computational Intelligence and Games (2012)

Over the past decades, video games have become increasingly popular and complex. Virtual worlds have gone a long way since the first arcades and so have the artificial intelligence (AI) techniques used to ... [more ▼]

Over the past decades, video games have become increasingly popular and complex. Virtual worlds have gone a long way since the first arcades and so have the artificial intelligence (AI) techniques used to control agents in these growing environments. Tasks such as world exploration, con- strained pathfinding or team tactics and coordination just to name a few are now default requirements for contemporary video games. However, despite its recent advances, video game AI still lacks the ability to learn. In this paper, we attempt to break the barrier between video game AI and machine learning and propose a generic method allowing real-time strategy (RTS) agents to learn production strategies from a set of recorded games using supervised learning. We test this imitative learning approach on the popular RTS title StarCraft II® and successfully teach a Terran agent facing a Protoss opponent new production strategies. [less ▲]

Detailed reference viewed: 113 (47 ULg)
Full Text
Peer Reviewed
See detailArtificial intelligence design for real-time strategy games
Safadi, Firas ULg; Fonteneau, Raphaël ULg; Ernst, Damien ULg

in NIPS Workshop on Decision Making with Multiple Imperfect Decision Makers (2011, December)

For now over a decade, real-time strategy (RTS) games have been challenging intelligence, human and artificial (AI) alike, as one of the top genre in terms of overall complexity. RTS is a prime example ... [more ▼]

For now over a decade, real-time strategy (RTS) games have been challenging intelligence, human and artificial (AI) alike, as one of the top genre in terms of overall complexity. RTS is a prime example problem featuring multiple interacting imperfect decision makers. Elaborate dynamics, partial observability, as well as a rapidly diverging action space render rational decision making somehow elusive. Humans deal with the complexity using several abstraction layers, taking decisions on different abstract levels. Current agents, on the other hand, remain largely scripted and exhibit static behavior, leaving them extremely vulnerable to flaw abuse and no match against human players. In this paper, we propose to mimic the abstraction mechanisms used by human players for designing AI for RTS games. A non-learning agent for StarCraft showing promising performance is proposed, and several research directions towards the integration of learning mechanisms are discussed at the end of the paper. [less ▲]

Detailed reference viewed: 215 (18 ULg)