Debmalya Mandal

regret bound (3) ground truth recovery (2) performative reinforcement learning (2) reinforcement learning (2) value iteration (2) online learning (2) episodic learning (1) transfer learning (1) few-shot learning (1) policy optimization (1) gradient estimation (1) game theory (1) convergence analysis (1) sample complexity (1) robust optimization (1) mechanism design (1) dynamic regret (1) model selection (1) corruption robustness (1) communication complexity (1)