publications

This may go out of date occasionally. Please check my Google Scholar for the most up-to-date list of publications.

2026

  1. fail_predictably.png
    Training Agents to Fail Predictably: Fine-Tuning for Forecastable Tail Risk
    Will Schwarzer, and Scott Niekum
    In Advances in Neural Information Processing Systems (NeurIPS) , 2026
    To appear
  2. sri.png
    Supervised Reward Inference
    Will Schwarzer, Jordan Schneider , Philip S. Thomas , and Scott Niekum
    In Reinforcement Learning Conference (RLC) , 2026
  3. dns.png
    Are Deep Speech Denoising Models Robust to Adversarial Noise?
    Will Schwarzer, Philip S. Thomas , Andrea Fanelli , and Xiaoyu Liu
    In International Conference on Learning Representations (ICLR) , 2026

2025

  1. evarl.png
    Evaluation-Aware Reinforcement Learning
    Shripad Vilasrao Deshmukh , Will Schwarzer, and Scott Niekum
    Sep 2025
  2. rlhf.png
    Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
    Yaswanth Chittepu , Blossom Metevier , Will Schwarzer, Austin Hoag , Scott Niekum , and Philip S. Thomas
    In Reinforcement Learning Conference (RLC) , Aug 2025