<ul><li>Hyperparameter optimisation is crucial for achieving strong performance in reinforcement learning (RL).</li><li>Probabilistic Curriculum Learning (PCL) is a curriculum learning strategy designed to improve RL performance.</li><li>This paper provides an empirical analysis of hyperparameter interactions and their effects on the performance of a PCL algorithm.</li><li>The study presents strategies to refine hyperparameter search spaces and introduces a novel SHAP-based interpretability approach for analyzing hyperparameter impacts in RL.</li></ul>

Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learning

Discover more