Peng Liu

reinforcement learning (5) zero-shot learning (3) contrastive learning (2) generalization bound (2) facial expression (2) feature extraction (2) knowledge distillation (2) attention mechanism (2) reward function (2) benchmark evaluation (2) convolutional neural network (2) language model (2) large language model (2) chain-of-thought reasoning (2) upper confidence bound (2) deep reinforcement learning (2) locomotion control (1) sequential decision-making (1) stochastic gradient descent (1) image generation (1)