I detta arbete jämfördes ett LSTM-nätverk med ett feedforward-nätverk för generellt Atari 2600 spelande. Prestandan definierades som poängen agenten får för ett visst spel. Hypotesen var att LSTM skulle prestera minst lika bra som feedforward och förhoppningsvis mycket bättre. För att svara på frågeställningen skapades två olika agenter, en med ett LSTM-nätverk och en med ett feedforward-nätverk. Experimenten utfördes på Stella emulatorn med hjälp av ramverket the Arcade Learning Environment (ALE). Hänsyn togs till Machado råd om inställningar för användning av ALE och hur agenter borde tränas och evalueras samtidigt. Agenterna utvecklades med hjälp av en genetisk algoritm. Resultaten visade att LSTM var minst lika bra som feedforward men båda metoderna blev slagna av Machados metoder. Toppoängen i varje spel jämfördes med Granfelts arbete som har varit en utgångspunkt för detta arbete.

General game playing is an area of artificial intelligence which focuses on creating agents capable of playing many games from some class. The agents receive the rules just before the match and therefore cannot be specialized for each game. Deepstack is the first artificial intelligence to beat professional human players in heads-up no-limit Texas hold'em poker. While it is specialized for poker, at its core is a general algorithm for playing two-player zero-sum games with imperfect information - continual resolving. In this thesis we introduce a general version of continual resolving and compare its performance against Online Outcome Sampling Monte Carlo Counterfactual Regret Minimization in several games.

Tabletop games have within recent years evolvedto become more and more complex, such as through the useof dynamic rules, permanently changing how the game worksafter a playthrough, and players playing different roles in thegame. This leads to unique challenges for Artificial Intelligence.A Tabletop Games Framework (TAG) is a framework intended topromote research within general AI for modern tabletop games.Rolling Horizon Evolutionary Algorithms (RHEA) are a typeof algorithms that have been applied to games with successin the past. By implementing a RHEA agent we can studyhow it compares to other types of agents such as Monte CarloTree Search and Random Mutation Hill Climbing agents. Ofparticular interest is the game Pandemic (2008), as the existingagents are unable to win at it.

While automated game playing systems like Deep Blue perform excellent within their domain, handling a different game or even a slight change of rules is impossible without intervention of the programmer. Considered a great challenge for Artificial Intelligence, General Game Playing is concerned with the development of techniques that enable computer programs to play arbitrary, possibly unknown n-player games given nothing but the game rules in a tailor-made description language. A key to success in this endeavour is the ability to reliably extract hidden game-specific features from a given game description automatically. An informed general game player can efficiently play a game by exploiting structural game properties to choose the currently most appropriate algorithm, to construct a suited heuristic, or to apply techniques that reduce the search space. In addition, an automated method for property extraction can provide valuable assistance for the discovery of specification bugs during game design by providing information about the mechanics of the currently specified game description. The recent extension of the description language to games with incomplete information and elements of chance further induces the need for the detection of game properties involving player knowledge in several stages of the game. In this thesis, we develop a formal proof method for the automatic acquisition of rich game-specific invariance properties. To this end, we first introduce a simple yet expressive property description language to address knowledge-free game properties which may involve arbitrary finite sequences of successive game states. We specify a semantic based on state transition systems over the Game Description Language, and develop a provably correct formal theory which allows to show the validity of game properties with respect to their semantic across all reachable game states. Our proof theory does not require to visit every single reachable state. Instead, it applies an induction principle on the game rules based on the generation of answer set programs, allowing to apply any off-the-shelf answer set solver to practically verify invariance properties even in complex games whose state space cannot totally be explored. To account for the recent extension of the description language to games with incomplete information and elements of chance, we correctly extend our induction method to properties involving player knowledge. With an extensive evaluation we show its practical applicability even in complex games.

Generellt spelande är ett forskningsområde fokuserat på att skapa AI som kan spela spel utan någon domänspecifik information. Detta arbete har undersökt elman-nätverks potential för generellt Atari-spelande genom att testa ett elman-nätverk och ett feedforward-nätverk via the Arcade Learning Environment. Nätverken använder en pixelrepresentation för att representera spelmiljön och baserar sina handlingar endast på den informationen. Agenterna testades på fyra spel varav två anses kräva en mer avancerad struktur än feedforward. Agenterna evalueras via deras toppoäng i spelen som testas och tränas via en genetisk algoritm. Resultaten visade att elman-strukturen inte presterar bättre än feedforward, dessutom erhölls ingen poäng i de avancerade spelen vilket tyder på att ett korttidsminne inte är tillräckligt för att spela dessa spel. Jämfört med tidigare forskning sågs en liten förbättring över liknande struktur vilket tyder på en förbättrad representation. För att förbättra resultaten i detta arbete borde ett större antal spel testas.

This thesis deals with general game playing agent systems. On the contrary with common agents, which are designed only for a specified task or a game, general game playing agents have to be able to play basically any arbitrary game described in a formal declarative language. The biggest challenge is that the game rules are not known beforehand, which makes it impossible to use some optimizations or to make a good heuristic function. The thesis consists of a theoretical and a practical part. The first part introduces the field of general game playing agents, defines the Game Description Language and covers construction of heuristic evaluation functions and their integration within the Monte Carlo tree search algorithm. In the practical part, a general method of creating a new heuristic function is presented, which is later integrated into a proper agent, which is compared then with other systems.

While automated game playing systems like Deep Blue perform excellent within their domain, handling a different game or even a slight change of rules is impossible without intervention of the programmer. Considered a great challenge for Artificial Intelligence, General Game Playing is concerned with the development of techniques that enable computer programs to play arbitrary, possibly unknown n-player games given nothing but the game rules in a tailor-made description language. A key to success in this endeavour is the ability to reliably extract hidden game-specific features from a given game description automatically. An informed general game player can efficiently play a game by exploiting structural game properties to choose the currently most appropriate algorithm, to construct a suited heuristic, or to apply techniques that reduce the search space. In addition, an automated method for property extraction can provide valuable assistance for the discovery of specification bugs during game design by providing information about the mechanics of the currently specified game description. The recent extension of the description language to games with incomplete information and elements of chance further induces the need for the detection of game properties involving player knowledge in several stages of the game. In this thesis, we develop a formal proof method for the automatic acquisition of rich game-specific invariance properties. To this end, we first introduce a simple yet expressive property description language to address knowledge-free game properties which may involve arbitrary finite sequences of successive game states. We specify a semantic based on state transition systems over the Game Description Language, and develop a provably correct formal theory which allows to show the validity of game properties with respect to their semantic across all reachable game states. Our proof theory does not require to visit every single reachable state. Instead, it applies an induction principle on the game rules based on the generation of answer set programs, allowing to apply any off-the-shelf answer set solver to practically verify invariance properties even in complex games whose state space cannot totally be explored. To account for the recent extension of the description language to games with incomplete information and elements of chance, we correctly extend our induction method to properties involving player knowledge. With an extensive evaluation we show its practical applicability even in complex games.

Com a crescente complexidade das aplicações e sistemas computacionais, atualmente tem se tornado importante o uso de formalismos de várias naturezas na representação e modelagem de problemas complexos, como os sistemas reativos e concorrentes. Este trabalho apresenta uma contribuição na Tecnologia Adaptativa e uma nova técnica no desenvolvimento de uma aplicação para execução de alguns tipos de jogos, (General Game Playing), cuja característica está associada à capacidade de o sistema tomar conhecimento das regras do jogo apenas em tempo de execução. Com esse trabalho, amplia-se a classe de problemas que podem ser estudados e analisados sob a perspectiva da Tecnologia Adaptativa, através dos Dispositivos Adaptativos Cooperantes. A aplicação desenvolvida como exemplo neste trabalho introduz uma nova ótica no desenvolvimento de aplicações para jogos gerais (GGP) e abre novos horizontes para a aplicação da Tecnologia Adaptativa, como a utilização das regras para extração de informação e inferência. / The complexity of computer applications has grown so much that several formalisms of different kinds became important nowadays. Many systems (e.g. reactive and concurrent ones) employ such formalisms to represent and model actual complex problems. This work contributes to the field of Adaptive Technology, and proposes a new approach for developing general game playing system, whose feature is the capability to play a game by acknowledging the game rules only at run time. This work expands the set of problems that can be studied and analyzed under the Adaptive Technology perspective, by means of cooperating adaptive devices. The developed application used a new approach for general game playing development bringing and widens the application field of Adaptive Technology with subjects related to information extraction and inference based in the devices rules.

Com a crescente complexidade das aplicações e sistemas computacionais, atualmente tem se tornado importante o uso de formalismos de várias naturezas na representação e modelagem de problemas complexos, como os sistemas reativos e concorrentes. Este trabalho apresenta uma contribuição na Tecnologia Adaptativa e uma nova técnica no desenvolvimento de uma aplicação para execução de alguns tipos de jogos, (General Game Playing), cuja característica está associada à capacidade de o sistema tomar conhecimento das regras do jogo apenas em tempo de execução. Com esse trabalho, amplia-se a classe de problemas que podem ser estudados e analisados sob a perspectiva da Tecnologia Adaptativa, através dos Dispositivos Adaptativos Cooperantes. A aplicação desenvolvida como exemplo neste trabalho introduz uma nova ótica no desenvolvimento de aplicações para jogos gerais (GGP) e abre novos horizontes para a aplicação da Tecnologia Adaptativa, como a utilização das regras para extração de informação e inferência. / The complexity of computer applications has grown so much that several formalisms of different kinds became important nowadays. Many systems (e.g. reactive and concurrent ones) employ such formalisms to represent and model actual complex problems. This work contributes to the field of Adaptive Technology, and proposes a new approach for developing general game playing system, whose feature is the capability to play a game by acknowledging the game rules only at run time. This work expands the set of problems that can be studied and analyzed under the Adaptive Technology perspective, by means of cooperating adaptive devices. The developed application used a new approach for general game playing development bringing and widens the application field of Adaptive Technology with subjects related to information extraction and inference based in the devices rules.

While in traditional computer game playing agents were designed solely for the purpose of playing one single game, General Game Playing is concerned with agents capable of playing classes of games. Given the game's rules and a few minutes time, the agent is supposed to play any game of the class and eventually win it. Since the game is unknown beforehand, previously optimized data structures or human-provided features are not applicable. Instead, the agent must derive a strategy on its own. One approach to obtain such a strategy is to analyze the game rules and create a state evaluation function that can be subsequently used to direct the agent to promising states in the match. In this thesis we will discuss existing methods and present a general approach on how to construct such an evaluation function. Each topic is discussed in a modular fashion and evaluated along the lines of quality and efficiency, resulting in a strong agent.