Search Results for author:
Found 2 papers, 0 papers with code
Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games
In this work, we explore and evaluate updating LLM used for candidate recommendation during the learning of the text based game as well to mitigate the reliance on the human annotated gameplays, which are costly to acquire.
Feature diversity in self-supervised learning
With numerous scaling factors defined in previous works, it would be interesting to investigate how these factors may affect overall generalization performance in the context of self-supervised learning with CNN models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
