ES Is More Than Just a Traditional Finite-Difference Approximator
This work highlights a key distinction in optimization approaches for deep reinforcement learning, with potential implications for robustness in AI systems.
The paper demonstrates that evolution strategies (ES) optimize for robustness to parameter perturbations, not just reward gradients, leading to more robust policies than traditional policy gradient methods in tasks like humanoid locomotion.
An evolution strategy (ES) variant based on a simplification of a natural evolution strategy recently attracted attention because it performs surprisingly well in challenging deep reinforcement learning domains. It searches for neural network parameters by generating perturbations to the current set of parameters, checking their performance, and moving in the aggregate direction of higher reward. Because it resembles a traditional finite-difference approximation of the reward gradient, it can naturally be confused with one. However, this ES optimizes for a different gradient than just reward: It optimizes for the average reward of the entire population, thereby seeking parameters that are robust to perturbation. This difference can channel ES into distinct areas of the search space relative to gradient descent, and also consequently to networks with distinct properties. This unique robustness-seeking property, and its consequences for optimization, are demonstrated in several domains. They include humanoid locomotion, where networks from policy gradient-based reinforcement learning are significantly less robust to parameter perturbation than ES-based policies solving the same task. While the implications of such robustness and robustness-seeking remain open to further study, this work's main contribution is to highlight such differences and their potential importance.