Robust adversarial reinforcement learning is an effective method to train agents to manage
uncertain disturbance and modeling errors in real environments. However, for systems that …

Reinforcement learning with adversarial training is currently a key method for improving the
robustness of DRL. However, in adversarial training, especially for unstable or disturbance …

Double inverted pendulum system is highly nonlinear and unstable system, thus its stability
is a matter of concern, particularly when the system components have parametric …