reinforcement learning; delayed reward; reward redistribution; return decomposition; bias-variance; credit assignment; LSTM

Success stories of deep reinforcement learning (RL) from high dimensional inputs such as pixels or large spatial layouts include achieving superhuman performance on Atari games [30, 37, 1], grandmaster levelinStarcraft II[50]andgrasping adiverse setofobjects with impressivesuccess rates and generalization with robots in the real world [21].

To better reuse the VLM resource and fully leverage its potential on different zero-shot image classification tasks, a promising strategy is selecting appropriate Pre-Trained VLMs from the VLM Zoo, relying solely on the text data of the target dataset without access to the dataset's images.

Definition 2(Informal (see Definition 5)). Definition 3(Informal (see Definition 6)).