Publications

publications by categories in reversed chronological order.

2025

  1. arXiv
    ObjectRL: An Object-Oriented Reinforcement Learning Codebase
    G. Baykal, A. Akgül, M. Haussmann, B. Tasdighi, and 3 more authors
    arXiv Preprint, 2025
  2. arXiv
    Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization
    A. Akgül, G. Baykal, M. Haussmann, and M. Kandemir
    arXiv Preprint, 2025

2024

  1. NeurIPS
    Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
    A. Akgül, M. Haussmann, and M. Kandemir
    In Neural Information Processing Systems, 2024
  2. AABI
    PAC-Bayesian Soft Actor-Critic Learning
    B. Tasdighi, A. Akgül, M. Haussmann, K.K. Brink, and 1 more author
    In Advances in Approximate Bayesian Inference Symposium, 2024
  3. ICLR
    Calibrating Bayesian UNet++ for Sub-Seasonal Forecasting
    B. Asan, Abdullah Akgül, A. Unal, M. Kandemir, and 1 more author
    In Tackling Climate Change with Machine Learning at ICLR 2024, 2024
  4. L4DC
    Continual Learning of Multi-modal Dynamics with External Memory
    Abdullah Akgül, G. Unal, and M. Kandemir
    In Proceedings of The 6th Annual Learning for Dynamics and Control Conference, 2024

2023

  1. arXiv
    BOF-UCB: A Bayesian-Optimistic Frequentist Algorithm for Non-Stationary Contextual Bandits
    N. Werge, A. Akgül, and M. Kandemir
    arXiv Preprint, 2023

2022

  1. ICLR
    Evidential Turing Processes
    M. Kandemir, Abdullah Akgül, M. Haussmann, and G. Unal
    In International Conference on Learning Representations, 2022
  2. FL-NeurIPS
    How to Combine Variational Bayesian Networks in Federated Learning
    A. Ozer, K.B. Buldu, Abdullah Akgül, and G. Unal
    In Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022), 2022