NIPS Proceedingsβ

Marek Petrik

6 Papers

  • Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs (2019)
  • Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes (2018)
  • Safe Policy Improvement by Minimizing Robust Baseline Regret (2016)
  • RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning (2014)
  • Robust Value Function Approximation Using Bilinear Programming (2009)
  • Biasing Approximate Dynamic Programming with a Lower Discount Factor (2008)