Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations Using a GAN

• URL: http://arxiv.org/abs/2105.12960v1
• Date: Thu, 27 May 2021 06:27:19 GMT
• Title: Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations Using a GAN
• Authors: Jacob Schrum, Benjamin Capps, Kirby Steckel, Vanessa Volz, Sebastian Risi
• Abstract summary: We propose a new hybrid approach that evolves CPPNs first, but allows the latent vectors to evolve later, and combines the benefits of both approaches. These approaches are evaluated in Super Mario Bros. and The Legend of Zelda.
• Score: 5.144809478361604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way to combine GAN outputs into a cohesive whole, which would be useful in many areas, such as video game level generation. Game levels often consist of several segments, sometimes repeated directly or with variation, organized into an engaging pattern. Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). Specifically, a CPPN can define latent vector GAN inputs as a function of geometry, which provides a way to organize level segments output by a GAN into a complete level. However, a collection of latent vectors can also be evolved directly, to produce more chaotic levels. Here, we propose a new hybrid approach that evolves CPPNs first, but allows the latent vectors to evolve later, and combines the benefits of both approaches. These approaches are evaluated in Super Mario Bros. and The Legend of Zelda. We previously demonstrated via divergent search (MAP-Elites) that CPPNs better cover the space of possible levels than directly evolved levels. Here, we show that the hybrid approach can cover areas that neither of the other methods can and achieves comparable or superior QD scores.

Related papers

• Distance Guided Generative Adversarial Network for Explainable Binary Classifications [16.217674670254382]
  We propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification.
  arXiv  Detail & Related papers  (2023-12-29T09:50:35Z)
• StyleGenes: Discrete and Efficient Latent Distributions for GANs [149.0290830305808]
  We propose a discrete latent distribution for Generative Adversarial Networks (GANs) Instead of drawing latent vectors from a continuous prior, we sample from a finite set of learnable latents. We take inspiration from the encoding of information in biological organisms.
  arXiv  Detail & Related papers  (2023-04-30T23:28:46Z)
• Combating Mode Collapse in GANs via Manifold Entropy Estimation [70.06639443446545]
  Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications. We propose a novel training pipeline to address the mode collapse issue of GANs.
  arXiv  Detail & Related papers  (2022-08-25T12:33:31Z)
• Top-N: Equivariant set and graph generation without exchangeability [61.24699600833916]
  We consider one-shot probabilistic decoders that map a vector-shaped prior to a distribution over sets or graphs. These functions can be integrated into variational autoencoders (VAE), generative adversarial networks (GAN) or normalizing flows. Top-n is a deterministic, non-exchangeable set creation mechanism which learns to select the most relevant points from a trainable reference set.
  arXiv  Detail & Related papers  (2021-10-05T14:51:19Z)
• Auto-Parsing Network for Image Captioning and Visual Question Answering [101.77688388554097]
  We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures. Specifically, we impose a Probabilistic Graphical Model (PGM) parameterized by the attention operations on each self-attention layer to incorporate sparse assumption.
  arXiv  Detail & Related papers  (2021-08-24T08:14:35Z)
• Epigenetic evolution of deep convolutional models [81.21462458089142]
  We build upon a previously proposed neuroevolution framework to evolve deep convolutional models. We propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator.
  arXiv  Detail & Related papers  (2021-04-12T12:45:16Z)
• Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man [0.0]
  This paper focuses on combining GAN-generated segments in a snaking pattern to create levels for Mega Man. Multiple GANs were trained on different types of segments to ensure better flow between segments.
  arXiv  Detail & Related papers  (2021-01-30T23:34:15Z)
• Positional Encoding as Spatial Inductive Bias in GANs [97.6622154941448]
  SinGAN shows impressive capability in learning internal patch distribution despite its limited effective receptive field. In this work, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators. We propose a new multi-scale training strategy and demonstrate its effectiveness in the state-of-the-art unconditional generator StyleGAN2.
  arXiv  Detail & Related papers  (2020-12-09T18:27:16Z)
• TOAD-GAN: Coherent Style Level Generation from a Single Example [24.039037782220017]
  We present TOAD-GAN, a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels. We demonstrate its application for Super Mario Bros. levels and are able to generate new levels of similar style in arbitrary sizes.
  arXiv  Detail & Related papers  (2020-08-04T13:44:50Z)
• Sequential Segment-based Level Generation and Blending using Variational Autoencoders [5.33024001730262]
  We train VAEs to learn a sequential model of segment generation such that generated segments logically follow from prior segments. We obtain a pipeline that enables the generation of arbitrarily long levels that progress in any of these four directions. In addition to generating more coherent levels of non-fixed length, this method also enables implicit blending of levels from separate games.
  arXiv  Detail & Related papers  (2020-07-17T04:11:51Z)
• CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation [8.719982934025417]
  CPPN2GAN can organize level segments output by a GAN into a complete level. This new CPPN2GAN approach is validated in both Super Mario Bros. and The Legend of Zelda.
  arXiv  Detail & Related papers  (2020-04-03T04:29:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.