Evolution-Guided Policy Gradient in Reinforcement Learning

TL;DR

This paper introduces Evolutionary Reinforcement Learning (ERL), a hybrid approach combining Evolutionary Algorithms and Deep Reinforcement Learning to improve exploration, credit assignment, and convergence in complex control tasks.

Contribution

The paper proposes ERL, a novel hybrid algorithm that integrates EAs with DRL, enhancing sample efficiency and learning stability in challenging environments.

Findings

ERL outperforms prior DRL and EA methods on continuous control benchmarks.

ERL effectively addresses exploration and credit assignment challenges.

The hybrid approach achieves faster learning and higher stability.

Abstract

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely sensitive to hyperparameters. Collectively, these challenges severely limit the applicability of these approaches to real-world problems. Evolutionary Algorithms (EAs), a class of black box optimization techniques inspired by natural evolution, are well suited to address each of these three challenges. However, EAs typically suffer from high sample complexity and struggle to solve problems that require optimization of a large number of parameters. In this paper, we introduce Evolutionary Reinforcement Learning (ERL), a hybrid algorithm that leverages the population of an EA to provide diversified data to train an RL agent, and reinserts the RL agent into the EA population periodically to inject gradient information into the EA. ERL inherits EA's ability of temporal credit assignment with a fitness metric, effective exploration with a diverse set of policies, and stability of a population-based approach and complements it with off-policy DRL's ability to leverage gradients for higher sample efficiency and faster learning. Experiments in a range of challenging continuous control benchmarks demonstrate that ERL significantly outperforms prior DRL and EA methods.