|
|
Coevolution of AI and level generation for Super Mario game
Flimmel, Július ; Černý, Vojtěch (advisor) ; Pilát, Martin (referee)
Procedural Content Generation is now used in many games to generate a wide variety of content. It often uses players controlled by Artificial Intelligence for its evaluation. PCG content can also be used when training AI players to achieve better generalization. In both of these fields, evolutionary algorithms are employed, but they are rarely used together. In this thesis, we use the coevolution of AI players and level generators for platformer game Super Mario. Coevolution's benefit is, that the AI players are evaluated by adapting level generators, and vice versa, level generators are evaluated by adapting AI players. This approach has two results. The first one is a creation of multiple level generators, each generating levels of gradually increased difficulty. Levels generated using a sequence of these generators also mirror the learning curve of the AI player. This can be useful also for human players playing the game for the first time. The second result is an AI player, which was evolved on gradually more difficult levels. Making it learn progressively may yield better results. Using the coevolution also doesn't require any training data set.
|
|
|
Coevolution of AI and level generation for Super Mario game
Flimmel, Július ; Černý, Vojtěch (advisor) ; Pilát, Martin (referee)
Procedural Content Generation is now used in many games to generate a wide variety of content. It often uses players controlled by Artificial Intelligence for its evaluation. PCG content can also be used when training AI players to achieve better generalization. In both of these fields, evolutionary algorithms are employed, but they are rarely used together. In this thesis, we use the coevolution of AI players and level generators for platformer game Super Mario. Coevolution's benefit is, that the AI players are evaluated by adapting level generators, and vice versa, level generators are evaluated by adapting AI players. This approach has two results. The first one is a creation of multiple level generators, each generating levels of gradually increased difficulty. Levels generated using a sequence of these generators also mirror the learning curve of the AI player. This can be useful also for human players playing the game for the first time. The second result is an AI player, which was evolved on gradually more difficult levels. Making it learn progressively may yield better results. Using the coevolution also doesn't require any training data set.
|
|
|
Pascal with Truffle
Flimmel, Július ; Horký, Vojtěch (advisor) ; Bednárek, David (referee)
Trupple is an unconventional Pascal interpreter built on top of Oracle's Truffle frame- work. By using this framework, it is virtually platform independent because it runs in Java Virtual Machine and can also easily communicate with other Truffle-based languages and Java itself. The interpreter builds an abstract syntax tree from any Pascal source code and consequently executes the tree from its root node. It supports Pascal according to ISO 7185 standard and implements some commonly used exten- sions introduced by Borland's Turbo Pascal compiler. In this work, we describe the architecture of the interpreter, important design decisions, used technologies and we also provide a brief performance evaluation of Trupple. 1
|
guest ::
