Figure - uploaded by Daniele Fernandes
Content may be subject to copyright.
![Implementation of the VanillaGAN architecture based on [Goodfellow et al. 2014].](profile/Daniele-Fernandes-3/publication/372947326/figure/tbl2/AS:11431281179679100@1691341492743/Implementation-of-the-VanillaGAN-architecture-based-on-Goodfellow-et-al-2014.png)
Source publication
![Implementation of DCGAN architecture based on [Radford et al. 2015].](profile/Daniele-Fernandes-3/publication/372947326/figure/tbl3/AS:11431281179640205@1691341493846/Implementation-of-DCGAN-architecture-based-on-Radford-et-al-2015_Q320.jpg)
Manual designing levels for games is a complex task, often demanding time and effort from the game designer. An option for this is using algorithms to generate such levels, improving its scalability. Currently, such procedural content generation methods can be guided by hand-crafted rules or, as in more recent approaches, by learning from existing...
Contexts in source publication
Context 1
... architecture proposed by [Goodfellow et al. 2014], composed of fully connected layers (Table 2), is adjusted according to the loss function described in Equation 1. The discriminator tries to maximize the loss function by learning to classify the output x into real -following the function D(x) -and the generated data G(z) into fake -following the function D(G(z)), where z refers to the latent space as input to the generator. ...Context 2
... architecture proposed by [Goodfellow et al. 2014], composed of fully connected layers (Table 2), is adjusted according to the loss function described in Equation 1. The discriminator tries to maximize the loss function by learning to classify the output x into real -following the function D(x) -and the generated data G(z) into fake -following the function D(G(z)), where z refers to the latent space as input to the generator. ...Similar publications
This paper assesses the implementation of the framework for building new Distinctive Features and design mathematics games. We explain how to design a typical mathematics game according to the learning needs of elementary school students. Next, we explain how to build new Distinctive features that are unique to students' needs and can be run in mat...
Citations
Procedural Content Generation algorithms aim to create unique and variable dungeon maps, ensuring that players encounter infinite maps in the game. This capability is essential to prevent repetitive environments, keeping players engaged and providing them with new challenges and discoveries. Machine learning techniques, such as Generative Adversarial Networks (GANs), have proven effective in generating data, although they may have specific limitations. This paper proposes a GAN-based approach for generating dungeon maps and introduces three optimizations to enhance the training process. Our approach achieves remarkable results in producing valid and varied maps compared to existing methods. We demonstrate that our approach outperforms other approaches by generating more valid maps with increased variability.
