Portfolio optimization through multidimensional action optimization using Amazon SageMaker RL
AWS Machine Learning Blog
MARCH 8, 2023
Action masking is an approach to solve RL problems that involve inadmissibility constraints in a sample efficient manner. As the name suggests, it involves masking any inadmissible actions by setting their sampling probability to zero. The following figure depicts the RL cycle with action masking. self.tvec+4*np.cos(2*math.pi*self.tvec/16)
Let's personalize your content