Hyperparameters in Contextual RL are Highly Situational

TL;DR

This paper investigates how hyperparameters in contextual reinforcement learning are highly environment-specific, affecting stability and requiring different configurations based on environmental context, which complicates optimization.

Contribution

It demonstrates that hyperparameters in contextual RL depend heavily on environmental factors and that hyperparameter optimization varies in difficulty across different settings.

Findings

Hyperparameters vary with environmental context.

Optimizing hyperparameters is more challenging in contextual RL.

Environmental awareness improves hyperparameter tuning.

Abstract

Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparameters found by automatic hyperparameter optimization (HPO) methods are not only dependent on the problem at hand, but even on how well the state describes the environment dynamics. Specifically, we show that agents in contextual RL require different hyperparameters if they are shown how environmental factors change. In addition, finding adequate hyperparameter configurations is not equally easy for both settings, further highlighting the need for research into how hyperparameters influence learning and generalization in RL.