Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning

TL;DR

This paper introduces Ancestral Reinforcement Learning (ARL), a novel method that combines Zeroth-Order Optimization and Genetic Algorithms to improve exploration and gradient estimation in reinforcement learning.

Contribution

ARL unifies ZOO and GA by using ancestor histories for gradient inference and maintaining policy diversity, with theoretical insights into its exploration capabilities.

Findings

ARL enhances exploration through implicit KL-regularization.

ARL extends the applicability of population-based RL algorithms.

Theoretical analysis supports improved exploration in ARL.

Abstract

Reinforcement Learning (RL) offers a fundamental framework for discovering optimal action strategies through interactions within unknown environments. Recent advancement have shown that the performance and applicability of RL can significantly be enhanced by exploiting a population of agents in various ways. Zeroth-Order Optimization (ZOO) leverages an agent population to estimate the gradient of the objective function, enabling robust policy refinement even in non-differentiable scenarios. As another application, Genetic Algorithms (GA) boosts the exploration of policy landscapes by mutational generation of policy diversity in an agent population and its refinement by selection. A natural question is whether we can have the best of two worlds that the agent population can have. In this work, we propose Ancestral Reinforcement Learning (ARL), which synergistically combines the robust gradient estimation of ZOO with the exploratory power of GA. The key idea in ARL is that each agent within a population infers gradient by exploiting the history of its ancestors, i.e., the ancestor population in the past, while maintaining the diversity of policies in the current population as in GA. We also theoretically reveal that the populational search in ARL implicitly induces the KL-regularization of the objective function, resulting in the enhanced exploration. Our results extend the applicability of populational algorithms for RL.