An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search

TL;DR

This paper presents AES-RL, an asynchronous framework that effectively combines evolution strategies and reinforcement learning, improving sample efficiency, stability, and time efficiency in continuous control tasks.

Contribution

It introduces a novel asynchronous framework for integrating ES and DRL, along with various update methods that leverage asynchronism for better performance.

Findings

AES-RL outperforms previous methods in continuous control benchmarks.

The asynchronous update schemes improve time efficiency and policy diversity.

The combined approach achieves superior stability and sample efficiency.

Abstract

Deep reinforcement learning (DRL) algorithms and evolution strategies (ES) have been applied to various tasks, showing excellent performances. These have the opposite properties, with DRL having good sample efficiency and poor stability, while ES being vice versa. Recently, there have been attempts to combine these algorithms, but these methods fully rely on synchronous update scheme, making it not ideal to maximize the benefits of the parallelism in ES. To solve this challenge, asynchronous update scheme was introduced, which is capable of good time-efficiency and diverse policy exploration. In this paper, we introduce an Asynchronous Evolution Strategy-Reinforcement Learning (AES-RL) that maximizes the parallel efficiency of ES and integrates it with policy gradient methods. Specifically, we propose 1) a novel framework to merge ES and DRL asynchronously and 2) various asynchronous update methods that can take all advantages of asynchronism, ES, and DRL, which are exploration and time efficiency, stability, and sample efficiency, respectively. The proposed framework and update methods are evaluated in continuous control benchmark work, showing superior performance as well as time efficiency compared to the previous methods.