Publication Details

AutoRL Hyperparameter Landscapes

authored by
Aditya Mohan, Carolin Benjamins, Konrad Wienecke, Alexander Dockhorn, Marius Lindauer

Although Reinforcement Learning (RL) has shown to be capable of producing impressive results, its use is limited by the impact of its hyperparameters on performance. This often makes it difficult to achieve good results in practice. Automated RL (AutoRL) addresses this difficulty, yet little is known about the dynamics of the hyperparameter landscapes that hyperparameter optimization (HPO) methods traverse in search of optimal configurations. In view of existing AutoRL approaches dynamically adjusting hyperparameter configurations, we propose an approach to build and analyze these hyperparameter landscapes not just for one point in time but at multiple points in time throughout training. Addressing an important open question on the legitimacy of such dynamic AutoRL approaches, we provide thorough empirical evidence that the hyperparameter landscapes strongly vary over time across representative algorithms from RL literature (DQN and SAC) in different kinds of environments (Cartpole and Hopper). This supports the theory that hyperparameters should be dynamically adjusted during training and shows the potential for more insights on AutoRL problems that can be gained through landscape analyses.

Automatic Image Interpretation Section
Institute of Information Processing
Machine Learning Section
Institute of Artificial Intelligence
Conference contribution
Publication date
Publication status
E-pub ahead of print
Electronic version(s) (Access: Open) (Access: Open)