Part of Advances in Neural Information Processing Systems 37 (NeurIPS 2024) Main Conference Track
Jacob Adkins, Michael Bowling, Adam White
The performance of modern reinforcement learning algorithms critically relieson tuning ever increasing numbers of hyperparameters. Often, small changes ina hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achieve state-of-the-artperformance reported in the literature. We currently lack a scalable and widelyaccepted approach to characterizing these complex interactions. This work proposes a new empirical methodology for studying, comparing, and quantifying thesensitivity of an algorithm’s performance to hyperparameter tuning for a given setof environments. We then demonstrate the utility of this methodology by assessingthe hyperparameter sensitivity of several commonly used normalization variants ofPPO. The results suggest that several algorithmic performance improvements may,in fact, be a result of an increased reliance on hyperparameter tuning.