This paper presents a training method for increasing performance of reinforcement learning agents. The method is named Environment Adversarial Reinforcement Learning. The method requires the reinforcement learning environment to be parameterizeable. Over the course of training, environment parameters are updated in a direction of increasing difficulty for the agent. The direction for these updates is found using a performance prediction network trained on data from tests of the agent under varying environment parameters. The method was tested on a CartPole environment. A 28-58\% improvement in mean return was found when comparing performance to a baseline reinforcement learning algorithm on both easy and hard versions of the task.
Environment Adversarial Reinforcement Learning
AIAA SciTech Forum and Exposition ; 2024 ; Orlando, FL, US
Miscellaneous
No indication
English
Environment Adversarial Reinforcement Learning
AIAA | 2024
|CERTIFIED ADVERSARIAL ROBUSTNESS FOR DEEP REINFORCEMENT LEARNING
European Patent Office | 2021
|Learning Aircraft Pilot Skills by Adversarial Inverse Reinforcement Learning
Springer Verlag | 2024
|