Deqiang Ouyang

contrastive learning (1) robust optimization (1) few-shot learning (1) game theory (1) bayesian optimization (1) thompson sampling (1) variational autoencoder (1) meta-reinforcement learning (1) exploration strategy (1) offline meta-reinforcement learning (1) parameter space (1) few-shot adaptation (1) structured noise (1) parameter space exploration (1) task-agnostic exploration (1) cross-task context (1) context shift (1) cvar optimization (1)