Le Gan

intrinsic reward (2) transfer learning (2) knowledge distillation (2) catastrophic forgetting (1) adversarial learning (1) few-shot learning (1) policy optimization (1) class-incremental learning (1) model aggregation (1) keyword spotting (1) partially observable markov decision process (1) model-based reinforcement learning (1) reward function (1) probability calibration (1) reward model (1) pre-trained model (1) bi-level optimization (1) world model (1) exploration strategy (1) unsupervised reinforcement learning (1)