Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learning
By: Llewyn Salt, Marcus Gallagher
Potential Business Impact:
Makes computer learning faster and easier.
Hyperparameter optimisation (HPO) is crucial for achieving strong performance in reinforcement learning (RL), as RL algorithms are inherently sensitive to hyperparameter settings. Probabilistic Curriculum Learning (PCL) is a curriculum learning strategy designed to improve RL performance by structuring the agent's learning process, yet effective hyperparameter tuning remains challenging and computationally demanding. In this paper, we provide an empirical analysis of hyperparameter interactions and their effects on the performance of a PCL algorithm within standard RL tasks, including point-maze navigation and DC motor control. Using the AlgOS framework integrated with Optuna's Tree-Structured Parzen Estimator (TPE), we present strategies to refine hyperparameter search spaces, enhancing optimisation efficiency. Additionally, we introduce a novel SHAP-based interpretability approach tailored specifically for analysing hyperparameter impacts, offering clear insights into how individual hyperparameters and their interactions influence RL performance. Our work contributes practical guidelines and interpretability tools that significantly improve the effectiveness and computational feasibility of hyperparameter optimisation in reinforcement learning.
Similar Papers
Probabilistic Curriculum Learning for Goal-Based Reinforcement Learning
Machine Learning (CS)
Teaches robots to learn new tasks by themselves.
ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
Machine Learning (CS)
Makes AI learn faster and better.
A General Approach of Automated Environment Design for Learning the Optimal Power Flow
Machine Learning (CS)
Teaches computers to solve power grid problems better.