Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks

• URL: http://arxiv.org/abs/2004.00151v1
• Date: Tue, 31 Mar 2020 22:52:17 GMT
• Title: Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks
• Authors: Jacob Schrum, Jake Gutierrez, Vanessa Volz, Jialin Liu, Simon Lucas, and Sebastian Risi
• Abstract summary: Latent Variable Evolution (LVE) has recently been applied to game levels. This paper introduces a tool for interactive LVE of tile-based levels for games. The tool also allows for direct exploration of the latent dimensions, and allows users to play discovered levels.
• Score: 8.091708140619946
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Adversarial Networks (GANs) are an emerging form of indirect encoding. The GAN is trained to induce a latent space on training data, and a real-valued evolutionary algorithm can search that latent space. Such Latent Variable Evolution (LVE) has recently been applied to game levels. However, it is hard for objective scores to capture level features that are appealing to players. Therefore, this paper introduces a tool for interactive LVE of tile-based levels for games. The tool also allows for direct exploration of the latent dimensions, and allows users to play discovered levels. The tool works for a variety of GAN models trained for both Super Mario Bros. and The Legend of Zelda, and is easily generalizable to other games. A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels. User feedback also indicates how this system could eventually grow into a commercial design tool, with the addition of a few enhancements.

Related papers

• Evaluating Environments Using Exploratory Agents [0.0]
  We investigate the using an exploratory agent to provide feedback on the design of procedurally generated game levels. Our study showed that our exploratory agent can clearly distinguish between engaging and unengaging levels.
  arXiv  Detail & Related papers  (2024-09-04T11:51:26Z)
• METRA: Scalable Unsupervised RL with Metric-Aware Abstraction [69.90741082762646]
  Metric-Aware Abstraction (METRA) is a novel unsupervised reinforcement learning objective. By learning to move in every direction in the latent space, METRA obtains a tractable set of diverse behaviors. We show that METRA can discover a variety of useful behaviors even in complex, pixel-based environments.
  arXiv  Detail & Related papers  (2023-10-13T06:43:11Z)
• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory [97.87093169454431]
  Ghost in the Minecraft (GITM) is a novel framework that integrates Large Language Models (LLMs) with text-based knowledge and memory. We develop a set of structured actions and leverage LLMs to generate action plans for the agents to execute. The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate.
  arXiv  Detail & Related papers  (2023-05-25T17:59:49Z)
• EDN: Salient Object Detection via Extremely-Downsampled Network [66.38046176176017]
  We introduce an Extremely-Downsampled Network (EDN), which employs an extreme downsampling technique to effectively learn a global view of the whole image. Experiments demonstrate that EDN achieves sArt performance with real-time speed.
  arXiv  Detail & Related papers  (2020-12-24T04:23:48Z)
• Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games [137.86426963572214]
  Turn-based strategy games like Roguelikes, for example, present unique challenges to Deep Reinforcement Learning (DRL) We propose two network architectures to better handle complex categorical state spaces and to mitigate the need for retraining forced by design decisions.
  arXiv  Detail & Related papers  (2020-12-07T08:47:25Z)
• Learning Affordance Landscapes for Interaction Exploration in 3D Environments [101.90004767771897]
  Embodied agents must be able to master how their environment works. We introduce a reinforcement learning approach for exploration for interaction. We demonstrate our idea with AI2-iTHOR.
  arXiv  Detail & Related papers  (2020-08-21T00:29:36Z)
• Co-generation of game levels and game-playing agents [4.4447051343759965]
  This paper introduces a POET-Inspired Neuroevolutionary System for KreativitY (PINSKY) in games. Results demonstrate the ability of PINSKY to generate curricula of game levels, opening up a promising new avenue for research at the intersection of content generation and artificial life.
  arXiv  Detail & Related papers  (2020-07-16T17:48:05Z)
• Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network [11.055580854275474]
  We show how designers may specify gameplay measures to our system and extract high-quality (playable) levels with a diverse range of level mechanics. An online user study shows how the different mechanics of the automatically generated levels affect subjective ratings of their perceived difficulty and appearance.
  arXiv  Detail & Related papers  (2020-07-11T03:38:06Z)
• Diagnosing the Environment Bias in Vision-and-Language Navigation [102.02103792590076]
  Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations. Recent works that study VLN observe a significant performance drop when tested on unseen environments, indicating that the neural agent models are highly biased towards training environments. In this work, we design novel diagnosis experiments via environment re-splitting and feature replacement, looking into possible reasons for this environment bias.
  arXiv  Detail & Related papers  (2020-05-06T19:24:33Z)
• Controllable Level Blending between Games using Variational Autoencoders [6.217860411034386]
  We train a VAE on level data from Super Mario Bros. and Kid Icarus, enabling it to capture the latent space spanning both games. We then use this space to generate level segments that combine properties of levels from both games. We argue that these affordances make the VAE-based approach especially suitable for co-creative level design.
  arXiv  Detail & Related papers  (2020-02-27T01:38:35Z)
• Learning to Generate Levels From Nothing [5.2508303190856624]
  We propose Generative Playing Networks which design levels for itself to play. The algorithm is built in two parts; an agent that learns to play game levels, and a generator that learns the distribution of playable levels. We demonstrate the capability of this framework by training an agent and level generator for a 2D dungeon crawler game.
  arXiv  Detail & Related papers  (2020-02-12T22:07:23Z)

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.