Pier Giuseppe Sessa

online learning (5) gaussian process (4) regret bound (4) no-regret learning (2) model-based reinforcement learning (2) game theory (2) coarse correlated equilibrium (2) online algorithm (2) multi-agent learning (2) sequential decision-making (1) markov decision process (1) reinforcement learning from human feedback (1) regret minimization (1) multi-agent reinforcement learning (1) multitask learning (1) sample complexity (1) robust optimization (1) bandit feedback (1) bayesian optimization (1) resource allocation (1)