Chih-wei Hsu

reinforcement learning (1) policy gradient (1) temporal dynamics (1) behavior cloning (1) model-based reinforcement learning (1) variance reduction (1) thompson sampling (1) multi-armed bandit (1) regret bound (1) foundation model (1) meta-reinforcement learning (1) controlled text generation (1) latent state inference (1) bayesian exploration (1) neural network (1) softmax policy (1) latent embedding space (1) bandit policy (1)