Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learning

• URL: http://arxiv.org/abs/2509.24341v1
• Date: Mon, 29 Sep 2025 06:43:33 GMT
• Title: Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learning
• Authors: Qingquan Zhang, Ziqi Wang, Yuchen Li, Keyuan Zhang, Bo Yuan, Jialin Liu,
• Abstract summary: This paper aims to expand horizons of level diversity by considering multi-dimensional diversity when training generative models.<n>We formulate the model training as a multi-objective learning problem, where each diversity metric is treated as a distinct objective.<n>A multi-objective evolutionary learning framework that optimises multiple diversity metrics simultaneously throughout the model training process is proposed.
• Score: 10.755666953578336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, the generation of diverse game levels has gained increasing interest, contributing to a richer and more engaging gaming experience. A number of level diversity metrics have been proposed in literature, which are naturally multi-dimensional, leading to conflicted, complementary, or both relationships among these dimensions. However, existing level generation approaches often fail to comprehensively assess diversity across those dimensions. This paper aims to expand horizons of level diversity by considering multi-dimensional diversity when training generative models. We formulate the model training as a multi-objective learning problem, where each diversity metric is treated as a distinct objective. Furthermore, a multi-objective evolutionary learning framework that optimises multiple diversity metrics simultaneously throughout the model training process is proposed. Our case study on the commonly used benchmark Super Mario Bros. demonstrates that our proposed framework can enhance multi-dimensional diversity and identify a Pareto front of generative models, which provides a range of tradeoffs among playability and two representative diversity metrics, including a content-based one and a player-centered one. Such capability enables decision-makers to make informed choices when selecting generators accommodating a variety of scenarios and the diverse needs of players and designers.

Related papers

• PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards [86.1965460124838]
  We propose a scalable multi-subject data generation pipeline.<n>We first enable single-subject personalization models to acquire knowledge of multi-image and multi-subject scenarios.<n>To enhance both subject consistency and text controllability, we design a set of Pairwise Subject-Consistency Rewards.
  arXiv  Detail & Related papers  (2025-12-01T03:25:49Z)
• VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills [0.0]
  In self-supervised reinforcement learning (RL), one of the key challenges is learning a diverse set of skills to prepare agents for unknown future tasks.<n>We introduce VendiRL, a unified framework for learning diversely diverse sets of skills.
  arXiv  Detail & Related papers  (2025-09-03T01:53:29Z)
• A survey of diversity quantification in natural language processing: The why, what, where and how [2.5833049611832273]
  We survey articles in the ACL Anthology from the past 6 years, with "diversity" or "diverse" in their title.<n>We put forward a unified taxonomy of why, what on, where, and how diversity is measured in NLP.<n>We believe that this study paves the way towards a better formalization of diversity in NLP.
  arXiv  Detail & Related papers  (2025-07-28T14:12:34Z)
• Evaluating the Diversity and Quality of LLM Generated Content [72.84945252821908]
  We introduce a framework for measuring effective semantic diversity--diversity among outputs that meet quality thresholds.<n>Although preference-tuned models exhibit reduced lexical and syntactic diversity, they produce greater effective semantic diversity than SFT or base models.<n>These findings have important implications for applications that require diverse yet high-quality outputs.
  arXiv  Detail & Related papers  (2025-04-16T23:02:23Z)
• Measuring Diversity of Game Scenarios [11.859929416550754]
  We aim to bridge the current gaps in literature and practice, offering insights into effective strategies for measuring and integrating diversity in game scenarios.<n>This survey not only charts a path for future research in diverse game scenarios but also serves as a handbook for industry practitioners seeking to leverage diversity as a key component of game design and development.
  arXiv  Detail & Related papers  (2024-04-15T07:59:52Z)
• Diversify Question Generation with Retrieval-Augmented Style Transfer [68.00794669873196]
  We propose RAST, a framework for Retrieval-Augmented Style Transfer. The objective is to utilize the style of diverse templates for question generation. We develop a novel Reinforcement Learning (RL) based approach that maximizes a weighted combination of diversity reward and consistency reward.
  arXiv  Detail & Related papers  (2023-10-23T02:27:31Z)
• Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction [125.18248926508045]
  We propose Channel-Exchanging-Network (CEN) which is self-adaptive, parameter-free, and more importantly, applicable for both multimodal fusion and multitask learning. CEN dynamically exchanges channels betweenworks of different modalities. For the application of dense image prediction, the validity of CEN is tested by four different scenarios.
  arXiv  Detail & Related papers  (2021-12-04T05:47:54Z)
• Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games [44.30509625560908]
  In open-ended learning algorithms, there are no widely accepted definitions for diversity, making it hard to construct and evaluate the diverse policies. We propose a unified measure of diversity in multi-agent open-ended learning based on both Behavioral Diversity (BD) and Response Diversity (RD) We show that many current diversity measures fall in one of the categories of BD or RD but not both. With this unified diversity measure, we design the corresponding diversity-promoting objective and population effectivity when seeking the best responses in open-ended learning.
  arXiv  Detail & Related papers  (2021-06-09T10:11:06Z)
• Embedded Deep Bilinear Interactive Information and Selective Fusion for Multi-view Learning [70.67092105994598]
  We propose a novel multi-view learning framework to make the multi-view classification better aimed at the above-mentioned two aspects. In particular, we train different deep neural networks to learn various intra-view representations. Experiments on six publicly available datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2020-07-13T01:13:23Z)
• Evaluating the Evaluation of Diversity in Natural Language Generation [43.05127848086264]
  We propose a framework for evaluating diversity metrics in natural language generation systems. Our framework can advance the understanding of different diversity metrics, an essential step on the road towards better NLG systems.
  arXiv  Detail & Related papers  (2020-04-06T20:44:10Z)

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.