Optimización de la humanidad de bots de Unreal Tournament 2004 mediante algoritmos evolutivos (Humanness optimization of Unreal Tournament 2004 bots by means of evolutionary algorithms)
نویسندگان
چکیده
This work describes three different approaches looking to get the best Bot (autonomous agent) for the First Person Shooter Unreal Tournament 2004. To this end, different hybridizations of the two best bots of the Botprize Competition 2014 are created. This competition decided the humanness level of the bots by means of a Turing test conducted on human judges. Thus, the proposal considers the source code of MirrorBot (winner) and NizorBot (second) and combines the best parts of their behaviour, in order to create a better human-like agent. Then, a Genetic Algorithm is applied to improve MirroBot’s behavioural parameters. All the approaches have been tested by human judges, by means of a Turing test for bots, based on a third person assessment (i.e. videos showing gameplay). According to the results, the evolutionary version of MirrorBot is the best implementation. One of the hybridizations also obtained a very good humanness level.
منابع مشابه
Strategic Planning for Unreal Tournament© Bots
We propose the use of hierarchical (HTN) planning techniques to encode strategies that one or more Bots should execute while acting in highly dynamic environments such as Unreal Tournament© games. Our approach allows the formulation of a grand strategy but retains the ability of Bots to react to the events in the environment while contributing to the grand strategy.
متن کاملUnrealGoal Bots - Conceptual Design of a Reusable Interface
It remains a challenge with current state of the art technology to use BDI agents to control real-time, dynamic and complex environments. We report on our effort to connect the Goal agent programming language to the real-time game Unreal Tournament 2004. BDI agents provide an interesting alternative to control bots in a game such as Unreal Tournament to more reactive styles of controlling such ...
متن کاملControlling Unreal Tournament 2004 Bots with the Logic-based Action Language GOLOG
Computer games and the accompanying entertainment industry branch has become a major market factor. AI techniques are successfully applied to tasks like path planning or intelligent swarm behavior. On the decision-making level the state of the art are state machines with a fixed set of behaviors. The perception of the computer player is perfect. They exactly know where the other players are loc...
متن کاملHumanlike Combat Behavior via Multiobjective Neuroevolution
Although evolution has proven to be a powerful search method for discovering effective behavior for sequential decision-making problems, it seems unlikely that evolving for raw performance could result in behavior that is distinctly humanlike. This chapter demonstrates how humanlike behavior can be evolved by restricting a bot’s actions in a way consistent with human limitations and predilectio...
متن کاملUnreal GOLOG Bots
Even though reasoning and, in particular, planning techniques have had a long tradition in Artificial Intelligence, these have only recently been applied to interactive computer games. In this paper we propose the use of READYLOG, a variant of the logic-based action language GOLOG, to build game bots. The language combines features from classical programming languages with decision-theoretic pl...
متن کامل