Evolutionary Reinforcement Learning

05/21/2018
by   Shauharda Khadka, et al.
0

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 with 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 benchmark tasks demonstrate that ERL significantly outperforms prior DRL and EA methods, achieving state-of-the-art performances.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/02/2019

Collaborative Evolutionary Reinforcement Learning

Deep reinforcement learning algorithms have been successfully applied to...
research
03/07/2023

Evolutionary Reinforcement Learning: A Survey

Reinforcement learning (RL) is a machine learning approach that trains a...
research
12/10/2020

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

Deep reinforcement learning (DRL) algorithms and evolution strategies (E...
research
04/19/2023

Evolving Constrained Reinforcement Learning Policy

Evolutionary algorithms have been used to evolve a population of actors ...
research
03/09/2023

Evolving Populations of Diverse RL Agents with MAP-Elites

Quality Diversity (QD) has emerged as a powerful alternative optimizatio...
research
11/29/2021

Physics-informed Evolutionary Strategy based Control for Mitigating Delayed Voltage Recovery

In this work we propose a novel data-driven, real-time power system volt...

Please sign up or login with your details

Forgot password? Click here to reset