Visualizing the Loss Landscape of Actor Critic Methods with Applications in Inventory Optimization

Understand

Continuous control is a widely applicable area of reinforcement learning.

• The main players of this area are actor-critic methods that utilize policy gradients of neural approximators as a common practice.
• The focus of our study is to show the characteristics of the actor loss function which is the essential part of the optimization.
• We exploit low dimensional visualizations of the loss function and provide comparisons for loss landscapes of various algorithms.