• Ovalle, A. & Lucas, S. M. (2023 in preparation). An information-theoretic criterion for world modelling in agents based on predicted relevance.
    [Poster]

  • Bamford, C., & Ovalle, A. (2021). Generalising Discrete Action Spaces with Conditional Action Trees. In 2021 IEEE Conference on Games (CoG) (pp. 1-8). IEEE.
    [PDF] [Talk]

  • Ovalle, A. (2021). An organismic inspired strategy for adaptive control. In ALIFE 2021: The 2021 Conference on Artificial Life. MIT Press.
    [PDF] [Talk]

  • Ovalle, A., & Lucas, S. M. (2021). Predictive Control Using Learned State Space Models via Rolling Horizon Evolution. ICAPS 2021: The International Conference on Automated Planning and Scheduling, Bridging the Gap Between AI Planning and Reinforcement Learning Workshop.
    [PDF] [Poster]

  • Ovalle, A., & Lucas, S. M. (2020). Modulation of viability signals for self-regulatory control. In International Workshop on Active Inference (pp. 101-113). Springer.
    [PDF] [Talk]

  • Ovalle, A., & Lucas, S. M. (2020). Bootstrapped model learning and error correction for planning with uncertainty in model-based RL. In 2020 IEEE Conference on Games (CoG) (pp. 495-502). IEEE.
    [PDF]

  • Ovalle, A. (2016). Deep reinforcement learning variants of multi-agent learning algorithms. MSc dissertation. University of Edinburgh.
    [PDF]