Kaizhao Yuan

reinforcement learning (1) few-shot learning (1) offline reinforcement learning (1) policy optimization (1) domain adaptation (1) prototype learning (1) data augmentation (1) code generation (1) instruction tuning (1) model-based reinforcement learning (1) uncertainty estimation (1) policy transfer (1) dynamics model (1) code model (1) large language model (1) conservative exploration (1)