Stability-Certified Reinforcement Learning via Spectral Normalization

no code implementations • 26 Dec 2020 • Ryoichi Takase, Nobuyuki Yoshikawa, Toshisada Mariyama, Takeshi Tsuchiya

While explicitly including the stability condition, the first method may provide an insufficient performance on the neural network controller due to its strict stability condition.

reinforcement-learning Reinforcement Learning (RL)