Andrei Lupu

multi-agent system (4) reinforcement learning (4) multi-agent reinforcement learning (2) covariate shift (2) game theory (2) zero-shot coordination (2) large language model (2) imitation learning (1) code generation (1) online learning (1) text generation (1) model safety (1) prompt engineering (1) partially observable (1) adversarial robustness (1) upper confidence bound (1) multi-armed bandit (1) adversarial attack (1) regret bound (1) minimax regret (1)