Search

RAIL Lab
RAIL Lab
  • Home
  • Projects
  • Publications
  • People
  • Join the Lab
  • Contact
  • Login
    Branden Ingram

    Branden Ingram

    Lecturer

    University of the Witwatersrand

      I have two main focuses, I know I know some might me call me an overachiever but I’m not the only one.

      The one focus of mine is learning and potentially replicating the A.I. systems and techniques utilised in popular games. However, this is not really considered “research” … apparently.

      So my other focus is the development of agents which can learn to perform optimally in various video game domains.

      Interests
      • Artificial Intelligence for Games
      • Reinforcement Learning

      Latest

      • Analysing the Effect of Latent Space Mutation Strategies for PCGML
      • Creating Diverse Play-Style-Centric Agents through Behavioural Cloning
      • Hierarchical WaveFunction Collapse
      • Play-style Identification and Player Modelling for Generating Tailored Advice in Video Games
      • Generating Interpretable Play-style Descriptions through Deep Unsupervised Clustering of Trajectories
      • Hierarchically Composing Level Generators for the Creation of Complex Structures
      • Real Time In-Game Playstyle Classification Using A Hybrid Probabilistic Supervised Learning Approach
      • Facilitating Safe Sim-to-Real through Simulator Abstraction and Zero-shot Task Composition
      • Improved Action Prediction through Multiple Model Processing of Player Trajectories
      • Play-style Identification through Deep Unsupervised Clustering of Trajectories

      Published with Wowchemy — the free, open source website builder that empowers creators.

      Cite
      Copy Download