Exploration in Action Space
This work provides theoretical insights for researchers in reinforcement learning, though it is incremental as it builds on existing exploration methods.
The paper analyzes when parameter space exploration outperforms action space exploration in reinforcement learning, showing theoretically and empirically that action space exploration is preferred when parametric complexity exceeds action dimensionality times horizon length.
Parameter space exploration methods with black-box optimization have recently been shown to outperform state-of-the-art approaches in continuous control reinforcement learning domains. In this paper, we examine reasons why these methods work better and the situations in which they are worse than traditional action space exploration methods. Through a simple theoretical analysis, we show that when the parametric complexity required to solve the reinforcement learning problem is greater than the product of action space dimensionality and horizon length, exploration in action space is preferred. This is also shown empirically by comparing simple exploration methods on several toy problems.