DSpace Repository

Browsing by Author "Schrum, Jacob"

Browsing by Author "Schrum, Jacob"

Sort by: Order: Results:

  • Schrum, Jacob; Lehman, Joel; Risi, Sebastian (ACM, 2016)
    An important challenge in neuroevolution is to evolve multimodal behavior. Indirect network encodings can potentially answer this challenge. Yet in practice, indirect encodings do not yield effective multimodal controllers. ...
  • Schrum, Jacob; Rollins, Alex C. (GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017-07)
    Previous research using evolutionary computation in Multi-Agent Systems indicates that assigning fitness based on team vs. individual behavior has a strong impact on the ability of evolved teams of artificial agents to ...
  • Schrum, Jacob; Gillespie, Lauren E.; Gonzalez, Gabriela R. (Proceedings of the Genetic and Evolutionary Computation Conference, 2017-07)
    Intelligent agents have a wide range of applications in robotics, video games, and computer simulations. However, fully general agents should function with as little human guidance as possible. Specifically, agents should ...
  • Schrum, Jacob; Miikkulainen, Risto (2008)
    It is difficult to discover effective behavior for NPCs automatically. For instance, evolutionary methods can learn sophisticated behaviors based on a single objective, but realistic game playing requires different ...
  • Friedman, Adina; Schrum, Jacob (Proceedings of the Conference on Games (CoG 2019), 2019)
    First-Person Shooter games are a popular genre that often includes a team deathmatch mode of play: teams of agents score by killing members of the other team. When played without other humans, this mode features both ...
  • Schrum, Jacob; Miikkulainen, Risto (IEEE, 2016)
    Ms. Pac-Man is a challenging video game in which multiple modes of behavior are required: Ms. Pac-Man must escape ghosts when they are threats and catch them when they are edible, in addition to eating all pills in each ...
  • Schrum, Jacob; McDonnell, Tyler; Andoni, Sari; Bonab, Elmira; Cheng, Sheila; Goode, Jimmie; Moore, Keith; Sellers, Gavin; Choi, Jun-Hwan (GECCO '18 Proceedings of the Genetic and Evolutionary Computation Conference, 2018-07)
    Neuroevolution is a powerful and general technique for evolving the structure and weights of artificial neural networks. Though neuroevolutionary approaches such as NeuroEvolution of Augmenting Topologies (NEAT) have been ...
  • Schrum, Jacob; Miikkulainen, Risto (ACM, 2010)
    Multiobjective evolutionary algorithms have long been applied to engineering problems. Lately they have also been used to evolve behaviors for intelligent agents. In such applications, it is often necessary to "shape" the ...
  • Schrum, Jacob (Proceedings of the Genetic and Evolutionary Computation Conference, 2018-07)
    Tetris is a challenging puzzle game that has received much attention from the AI community, but much of this work relies on intelligent high-level features. Recently, agents played the game using low-level features (10 X ...
  • Schrum, Jacob; Volz, Vanessa; Lucas, Simon M.; Smith, Adam; Liu, Jialin; Risi, Sebastian (Proceedings of the Genetic and Evolutionary Computation Conference, 2018-07)
    Generative Adversarial Networks (GANs) are a machine learning approach capable of generating novel example outputs across a space of provided training examples. Procedural Content Generation (PCG) of levels for video games ...
  • Schrum, Jacob; Miikkulainen, Risto (IEEE, 2009)
    Evolution is often successful in generating complex behaviors, but evolving agents that exhibit distinctly different modes of behavior under different circumstances (multi-modal behavior) is both difficult and time consuming. ...
  • Schrum, Jacob; Miikkulainen, Risto (ACM, 2014)
    Ms. Pac-Man is a challenging video game in which multiple modes of behavior are required to succeed: Ms. Pac-Man must escape ghosts when they are threats, and catch them when they are edible, in addition to eating all pills ...
  • Schrum, Jacob; Miikkulainen, Risto (IEEE, 2011)
    Intelligent opponent behavior helps make video games interesting to human players. Evolutionary computation can discover such behavior, especially when the game consists of a single task. However, multitask domains, in ...
  • Schrum, Jacob; Miikkulainen, Risto (IEEE, 2012)
    Intelligent opponent behavior makes video games interesting to human players. Evolutionary computation can discover such behavior, however, it is challenging to evolve behavior that consists of multiple separate tasks. ...
  • Hollingsworth, Bryan; Schrum, Jacob (Proceedings of the Congress on Evolutionary Computation (CEC 2019), 2019)
    Procedural Content Generation (PCG) has been used extensively in video games as both a cost saving measure and a means to increase replayability. Evolutionary computation is an approach to PCG that has the ability to ...
  • Price, William; Schrum, Jacob (Proceedings of the Congress on Evolutionary Computation (CEC 2019), 2019)
    Ms. Pac-Man is a well-known video game used extensively in AI research. Past research has focused on the standard, fully observable version of Ms. Pac-Man. Recently, a partially observable variant of the game has been used ...
  • Krolikowski, Anna; Friday, Sarah; Quintanilla, Alice; Schrum, Jacob (EvoMUSART: International Conference on Computational Intelligence in Music, Sound, Art, and Design, 2020)
    This paper demonstrates a computational approach to generating art reminiscent of Zentangles by combining Picbreeder with Wave Function Collapse (WFC). Picbreeder interactively evolves images based on user preferences, and ...
  • Schrum, Jacob; Tweraser, Isabel; Gillespie, Lauren E. (Proceedings of the Genetic and Evolutionary Computation Conference, 2018-07)
    Compositional Pattern Producing Networks (CPPNs) are a generative encoding that has been used to evolve a variety of novel artifacts, such as 2D images, 3D shapes, audio timbres, soft robots, and neural networks. This paper ...
  • Schrum, Jacob; Miikkulainen, Risto (ACM, 2015)
    Many challenging sequential decision-making problems require agents to master multiple tasks, such as defense and offense in many games. Learning algorithms thus benefit from having separate policies for these tasks, and ...