Search Results for author:
Found 2 papers, 0 papers with code
Information Content Exploration
We expand on this topic and propose a new intrinsic reward that systemically quantifies exploratory behavior and promotes state coverage by maximizing the information content of a trajectory taken by an agent.
Scope Loss for Imbalanced Classification and RL Exploration
From our analysis of the aforementioned problems we derive a novel loss function for reinforcement learning and supervised classification.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
