Guangxiang Zhu

model-based reinforcement learning (4) sample efficiency (3) overestimation bia (2) self-supervised learning (1) data augmentation (1) mutual information (1) value function (1) episodic memory (1) continuous control (1) value function approximation (1) value function estimation (1) bellman operator (1) convolutional neural network (1) world model (1) distributional shift (1) trajectory planning (1) dynamics learning (1) model-based rl (1) double q-learning (1) non-parametric memory (1)