Giorgia Ramponi

4 papers Department of Informatics, University of Zurich, University of Zurich

• Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
• Non-rectangular Robust MDPs with Normed Uncertainty Sets
• On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
• On the Convergence of Single-Timescale Actor-Critic