 Solving Non-Rectangular Reward-Robust MDPs via Frequency RegularizationAAAI Conference on Artificial Intelligence (AAAI), 2023 |
 Robust Reinforcement Learning via Genetic CurriculumIEEE International Conference on Robotics and Automation (ICRA), 2022 |
 The Geometry of Robust Value FunctionsInternational Conference on Machine Learning (ICML), 2022 |
 Twice regularized MDPs and the equivalence between robustness and
regularizationNeural Information Processing Systems (NeurIPS), 2021 |
 Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement
LearningNeural Information Processing Systems (NeurIPS), 2020 |
 Epistemic Risk-Sensitive Reinforcement LearningThe European Symposium on Artificial Neural Networks (ESANN), 2019 |
 A Bayesian Approach to Robust Reinforcement LearningConference on Uncertainty in Artificial Intelligence (UAI), 2019 |
 Soft-Robust Actor-Critic Policy-GradientConference on Uncertainty in Artificial Intelligence (UAI), 2018 |
 Risk-Sensitive and Robust Decision-Making: a CVaR Optimization ApproachNeural Information Processing Systems (NeurIPS), 2015 |
