Jacob Schrum
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jacob Schrum has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
Risto Miikkulainen
University of Texas at Austin
9 shared publications- Risto Miikkulainen
Department of Computer Science, University of Texas at Austin, Austin, USA
4 shared publications Sebastian Risi
3 shared publicationsBenjamin Capps
2 shared publications- Igor V. Karpov
The University of Texas at Austin
2 shared publications Joel Lehman
IT University of Copenhagen, Copenhagen, Denmark
2 shared publications
Latest Publications
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 633-636
Multi-Objective Evolutionary Design of Molecules with Enhanced Nonlinear Optical Properties
Nonlinear optical (NLO) materials are essential for many photonic, telecommunication, and laser technologies, yet discovering better NLO molecules is computationally challenging due to the vast chemical space and competing objectives. We compare evolutionary algorithms for molecular design with multiple objectives. We encode molecules as SMILES strings and evaluate their properties using quantum-chemical calculations. We compare NSGA-II, MAP-Elites, MOME, a single-objective (μ + λ) EA, and simulated annealing. Quality Diversity methods maintain archives across a measure space defined by atom and bond count, enabling the discovery of structurally diverse molecules. Our results demonstrate that NSGA-II consistently earns high scores in every objective, leading to high-quality molecules, but MOME does a better job exploring a wide range of possibilities, resulting in higher global hypervolume and MOQD scores. However, each method has strengths and weaknesses, and produced many promising molecules.
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 633-636
Open AccessMulti-Objective Evolutionary Design of Molecules with Enhanced Nonlinear Optical Properties
Nonlinear optical (NLO) materials are essential for many photonic, telecommunication, and laser technologies, yet discovering better NLO molecules is computationally challenging due to the vast chemical space and competing objectives. We compare evolutionary algorithms for molecular design with multiple objectives. We encode molecules as SMILES strings and evaluate their properties using quantum-chemical calculations. We compare NSGA-II, MAP-Elites, MOME, a single-objective (μ + λ) EA, and simulated annealing. Quality Diversity methods maintain archives across a measure space defined by atom and bond count, enabling the discovery of structurally diverse molecules. Our results demonstrate that NSGA-II consistently earns high scores in every objective, leading to high-quality molecules, but MOME does a better job exploring a wide range of possibilities, resulting in higher global hypervolume and MOQD scores. However, each method has strengths and weaknesses, and produced many promising molecules.
- Open Access
- 7 November 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Vol. 21 (1) , 110-120
Text-to-Level Diffusion Models with Various Text Encoders for Super Mario Bros
Recent research shows how diffusion models can unconditionally generate tile-based game levels, but use of diffusion models for text-to-level generation is underexplored. There are practical considerations for creating a usable model: caption/level pairs are needed, as is a text embedding model, and a way of generating entire playable levels, rather than individual scenes. We present strategies to automatically assign descriptive captions to an existing level dataset, and train diffusion models using both pretrained text encoders and simple transformer models trained from scratch. Captions are automatically assigned to generated levels so that the degree of overlap between input and output captions can be compared. We also assess the diversity and playability of the resulting levels. Results are compared with an unconditional diffusion model and a generative adversarial network, as well as the text-to-level approaches Five-Dollar Model and MarioGPT. Notably, the best diffusion model uses a simple transformer model for text embedding, and takes less time to train than diffusion models employing more complex text encoders, indicating that reliance on larger language models is not necessary. We also present a GUI allowing designers to construct long levels from model-generated scenes.
- 7 November 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Vol. 21 (1) , 110-120
Open AccessText-to-Level Diffusion Models with Various Text Encoders for Super Mario Bros
Recent research shows how diffusion models can unconditionally generate tile-based game levels, but use of diffusion models for text-to-level generation is underexplored. There are practical considerations for creating a usable model: caption/level pairs are needed, as is a text embedding model, and a way of generating entire playable levels, rather than individual scenes. We present strategies to automatically assign descriptive captions to an existing level dataset, and train diffusion models using both pretrained text encoders and simple transformer models trained from scratch. Captions are automatically assigned to generated levels so that the degree of overlap between input and output captions can be compared. We also assess the diversity and playability of the resulting levels. Results are compared with an unconditional diffusion model and a generative adversarial network, as well as the text-to-level approaches Five-Dollar Model and MarioGPT. Notably, the best diffusion model uses a simple transformer model for text embedding, and takes less time to train than diffusion models employing more complex text encoders, indicating that reliance on larger language models is not necessary. We also present a GUI allowing designers to construct long levels from model-generated scenes.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1471-1479
A Quality Diversity Approach to Evolving Model Rockets
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1471-1479
Open AccessA Quality Diversity Approach to Evolving Model Rockets
- 5 January 2024
- Published by Springer Nature
- p. 457-466
Constructing Game Agents Through Simulated Evolution
- 5 January 2024
- Published by Springer Nature
- p. 457-466
Constructing Game Agents Through Simulated Evolution
- Open Access
- 12 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1418-1426
Evolving Flying Machines in Minecraft Using Quality Diversity
Minecraft is a great testbed for human creativity that has inspired the design of various structures and even functioning machines, including flying machines. EvoCraft is an API for programmatically generating structures in Minecraft, but the initial work in this domain was not capable of evolving flying machines. This paper applies fitness-based evolution and quality diversity search in order to evolve flying machines. Although fitness alone can occasionally produce flying machines, thanks in part to a more sophisticated fitness function than was used previously, the quality diversity algorithm MAP-Elites is capable of discovering flying machines much more reliably, at least when an appropriate behavior characterization is used to guide the search for diverse solutions.
- 12 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1418-1426
Open AccessEvolving Flying Machines in Minecraft Using Quality Diversity
Minecraft is a great testbed for human creativity that has inspired the design of various structures and even functioning machines, including flying machines. EvoCraft is an API for programmatically generating structures in Minecraft, but the initial work in this domain was not capable of evolving flying machines. This paper applies fitness-based evolution and quality diversity search in order to evolve flying machines. Although fitness alone can occasionally produce flying machines, thanks in part to a more sophisticated fitness function than was used previously, the quality diversity algorithm MAP-Elites is capable of discovering flying machines much more reliably, at least when an appropriate behavior characterization is used to guide the search for diverse solutions.
- Open Access
- 17 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 15 (1) , 1-4
Guest Editorial: Special Issue on Evolutionary Computation for Games
The eight papers in this special section focus on applications of evolutionary computation to games to demonstrate several ways in which evolution can push boundaries and explore new areas of what is possible in the realm of games research, with a focus on game-playing, automatic agent parameter tuning, automatic game testing, and procedural content generation.
- 17 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 15 (1) , 1-4
Open AccessGuest Editorial: Special Issue on Evolutionary Computation for Games
The eight papers in this special section focus on applications of evolutionary computation to games to demonstrate several ways in which evolution can push boundaries and explore new areas of what is possible in the realm of games research, with a focus on game-playing, automatic agent parameter tuning, automatic game testing, and procedural content generation.
- Open Access
Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations
Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search. Much previous work applying GANs to level generation focuses on fixed-size segments combined into a whole level, but individual segments may not fit together cohesively. In contrast, segments in human designed levels are often repeated, directly or with variation, and organized into patterns (the symmetric eagle in Level 1 of The Legend of Zelda, or repeated pipe motifs in Super Mario Bros). Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). CPPNs define latent vector GAN inputs as a function of geometry, organizing segments output by a GAN into complete levels. However, collections of latent vectors can also be evolved directly, producing more chaotic levels. We propose a hybrid approach that evolves CPPNs first, but allows latent vectors to evolve later, combining the benefits of both approaches. These approaches are evaluated in Super Mario Bros. and The Legend of Zelda. We previously demonstrated via a Quality-Diversity algorithm that CPPNs better cover the space of possible levels than directly evolved levels. Here, we show that the hybrid approach (1) covers areas that neither of the other methods can, and (2) achieves comparable or superior QD scores.
Open AccessHybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations
Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search. Much previous work applying GANs to level generation focuses on fixed-size segments combined into a whole level, but individual segments may not fit together cohesively. In contrast, segments in human designed levels are often repeated, directly or with variation, and organized into patterns (the symmetric eagle in Level 1 of The Legend of Zelda, or repeated pipe motifs in Super Mario Bros). Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). CPPNs define latent vector GAN inputs as a function of geometry, organizing segments output by a GAN into complete levels. However, collections of latent vectors can also be evolved directly, producing more chaotic levels. We propose a hybrid approach that evolves CPPNs first, but allows latent vectors to evolve later, combining the benefits of both approaches. These approaches are evaluated in Super Mario Bros. and The Legend of Zelda. We previously demonstrated via a Quality-Diversity algorithm that CPPNs better cover the space of possible levels than directly evolved levels. Here, we show that the hybrid approach (1) covers areas that neither of the other methods can, and (2) achieves comparable or superior QD scores.
- 27 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 15 (1) , 46-55
Hybrid Encoding for Generating Large Scale Game Level Patterns With Local Variations
Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search. Much previous work applying GANs to level generation focuses on fixed-size segments combined into a whole level, but individual segments may not fit together cohesively. In contrast, segments in human designed levels are often repeated, directly or with variation, and organized into patterns (the symmetric eagle in Level 1 of The Legend of Zelda, or repeated pipe motifs in Super Mario Bros). Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). CPPNs define latent vector GAN inputs as a function of geometry, organizing segments output by a GAN into complete levels. However, collections of latent vectors can also be evolved directly, producing more chaotic levels. We propose a hybrid approach that evolves CPPNs first, but allows latent vectors to evolve later, combining the benefits of both approaches. These approaches are evaluated in Super Mario Bros. and The Legend of Zelda. We previously demonstrated via a Quality-Diversity algorithm that CPPNs better cover the space of possible levels than directly evolved levels. Here, we show that the hybrid approach (1) covers areas that neither of the other methods can, and (2) achieves comparable or superior QD scores.
- 27 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 15 (1) , 46-55
Hybrid Encoding for Generating Large Scale Game Level Patterns With Local Variations
Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search. Much previous work applying GANs to level generation focuses on fixed-size segments combined into a whole level, but individual segments may not fit together cohesively. In contrast, segments in human designed levels are often repeated, directly or with variation, and organized into patterns (the symmetric eagle in Level 1 of The Legend of Zelda, or repeated pipe motifs in Super Mario Bros). Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). CPPNs define latent vector GAN inputs as a function of geometry, organizing segments output by a GAN into complete levels. However, collections of latent vectors can also be evolved directly, producing more chaotic levels. We propose a hybrid approach that evolves CPPNs first, but allows latent vectors to evolve later, combining the benefits of both approaches. These approaches are evaluated in Super Mario Bros. and The Legend of Zelda. We previously demonstrated via a Quality-Diversity algorithm that CPPNs better cover the space of possible levels than directly evolved levels. Here, we show that the hybrid approach (1) covers areas that neither of the other methods can, and (2) achieves comparable or superior QD scores.
- Open Access
Generative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zelda
Generative Adversarial Networks (GANs) have demonstrated their ability to learn patterns in data and produce new exemplars similar to, but different from, their training set in several domains, including video games. However, GANs have a fixed output size, so creating levels of arbitrary size for a dungeon crawling game is difficult. GANs also have trouble encoding semantic requirements that make levels interesting and playable. This paper combines a GAN approach to generating individual rooms with a graph grammar approach to combining rooms into a dungeon. The GAN captures design principles of individual rooms, but the graph grammar organizes rooms into a global layout with a sequence of obstacles determined by a designer. Room data from The Legend of Zelda is used to train the GAN. This approach is validated by a user study, showing that GAN dungeons are as enjoyable to play as a level from the original game, and levels generated with a graph grammar alone. However, GAN dungeons have rooms considered more complex, and plain graph grammar's dungeons are considered least complex and challenging. Only the GAN approach creates an extensive supply of both layouts and rooms, where rooms span across the spectrum of those seen in the training set to new creations merging design principles from multiple rooms.
Open AccessGenerative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zelda
Generative Adversarial Networks (GANs) have demonstrated their ability to learn patterns in data and produce new exemplars similar to, but different from, their training set in several domains, including video games. However, GANs have a fixed output size, so creating levels of arbitrary size for a dungeon crawling game is difficult. GANs also have trouble encoding semantic requirements that make levels interesting and playable. This paper combines a GAN approach to generating individual rooms with a graph grammar approach to combining rooms into a dungeon. The GAN captures design principles of individual rooms, but the graph grammar organizes rooms into a global layout with a sequence of obstacles determined by a designer. Room data from The Legend of Zelda is used to train the GAN. This approach is validated by a user study, showing that GAN dungeons are as enjoyable to play as a level from the original game, and levels generated with a graph grammar alone. However, GAN dungeons have rooms considered more complex, and plain graph grammar's dungeons are considered least complex and challenging. Only the GAN approach creates an extensive supply of both layouts and rooms, where rooms span across the spectrum of those seen in the training set to new creations merging design principles from multiple rooms.
- 9 April 2020
- Published by Springer Nature
- p. 49-65
Quantum Zentanglement: Combining Picbreeder and Wave Function Collapse to Create Zentangles®
- 9 April 2020
- Published by Springer Nature
- p. 49-65
Quantum Zentanglement: Combining Picbreeder and Wave Function Collapse to Create Zentangles®