Alexandre Galashov

reinforcement learning (2) transfer learning (2) continual learning (2) probabilistic modeling (1) imitation learning (1) variational inference (1) information bottleneck (1) data augmentation (1) hierarchical reinforcement learning (1) gaussian process (1) importance sampling (1) mutual information (1) policy iteration (1) visual classification (1) off-policy learning (1) sequential learning (1) off-policy reinforcement learning (1) distributional shift (1) non-stationary learning (1) parameter reset (1)