Adam Wierman

Distributionally Robust Cooperative Multi-agent Reinforcement Learning with Value Factorization

Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach

Maximizing the Value of Predictions in Control: Accuracy Is Not Enough

Conformal Risk Training: End-to-End Optimization of Conformal Risk Control

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees

SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer

Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

Fairness-Regularized Online Optimization with Switching Costs

Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning

Fusing Reward and Dueling Feedback in Stochastic Bandits

Online Robust Reinforcement Learning Through Monte-Carlo Planning

Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning

Adversarial Attacks on Cooperative Multi-agent Bandits