Audrey Durand

reinforcement learning (3) multi-armed bandit (2) regret bound (2) active learning (2) markov decision process (2) upper confidence bound (2) imitation learning (1) online learning (1) regret analysis (1) uncertainty quantification (1) knowledge transfer (1) data augmentation (1) incremental learning (1) adversarial training (1) prior knowledge (1) curriculum learning (1) discount factor (1) exploration-exploitation tradeoff (1) ensemble learning (1) deep learning (1)