Hyperparameters in Contextual RL are Highly Situational
Eimer, Theresa, Benjamins, Carolin, Lindauer, Marius
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Dec-21-2022
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States (0.04)
- Puerto Rico > San Juan
- San Juan (0.04)
- Oceania > Australia
- Genre:
- Research Report > New Finding (0.48)
- Industry:
- Health & Medicine (0.47)
- Technology: