Paper 'Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets' accepted at SIAM Journal on Optimization (SIOPT)
Paper 'Distributional Adversarial Attacks and Training in Deep Hedging' accepted to NeurIPS 2025
Paper 'Probabilistic Verification of Neural Networks using Branch and Bound' accepted at ICML 2025
Paper 'Computing Optimal Joint Chance Constrained Control Policies' accepted to IEEE Transactions on Automatic Control
Two papers accepted at NeurIPS 2024: 'Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces' and 'Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms'
Paper 'Regularized Q-learning through Robust Averaging' accepted at ICML 2024
ETH Medal for Outstanding Doctoral Thesis – 2018
IEEE George S. Axelby Outstanding Paper Award – 2016