Understanding the impact of entropy on policy optimization
This provides insights into the challenges of designing general-purpose policy optimization algorithms, but it is incremental as it builds on existing entropy regularization methods.
The paper analyzes how entropy regularization affects policy optimization in reinforcement learning, showing that higher entropy can smooth the optimization landscape and allow larger learning rates in some environments.
Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim using new visualizations of the optimization landscape based on randomly perturbing the loss function. We first show that even with access to the exact gradient, policy optimization is difficult due to the geometry of the objective function. Then, we qualitatively show that in some environments, a policy with higher entropy can make the optimization landscape smoother, thereby connecting local optima and enabling the use of larger learning rates. This paper presents new tools for understanding the optimization landscape, shows that policy entropy serves as a regularizer, and highlights the challenge of designing general-purpose policy optimization algorithms.