Reinforcement Learning Algorithms with Python

Natural gradient complications

Despite knowing the usefulness of the natural gradient in the RL framework, one of the major drawbacks of it is the computational cost that involves the calculation of FIM. While the computation of the gradient has a computational cost of , the natural gradient has a computational cost of , where is the number of parameters. In fact, in the NPG paper that dates back to 2003, the algorithm has been applied to very ...