Open kihyukh opened 2 years ago
Follow https://arxiv.org/pdf/2203.08409.pdf with perhaps a slight modification to implement a safe ddqn algorithm that can handle constraints by adaptively learning the lagrange multiplier.
Follow https://arxiv.org/pdf/2203.08409.pdf with perhaps a slight modification to implement a safe ddqn algorithm that can handle constraints by adaptively learning the lagrange multiplier.