Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

Amjad Yousef Majid, Serge Saaybi, Vincent Francois-Lavet, Ranga Venkatesha Prasad, Chris Verhoeven

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)

Abstract

Deep reinforcement learning (DRL) and evolution strategies (ESs) have surpassed human-level control in many sequential decision-making problems, yet many open challenges still exist. To get insights into the strengths and weaknesses of DRL versus ESs, an analysis of their respective capabilities and limitations is provided. After presenting their fundamental concepts and algorithms, a comparison is provided on key aspects, such as scalability, exploration, adaptation to dynamic environments, and multiagent learning. Current research challenges are also discussed, including sample efficiency, exploration versus exploitation, dealing with sparse rewards, and learning to plan. Then, the benefits of hybrid algorithms that combine DRL and ESs are highlighted.

Original languageEnglish
Pages (from-to)1-19
Number of pages19
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
Publication statusAccepted/In press - 2023

Keywords

  • Deep learning
  • Deep reinforcement learning (DRL)
  • Evolution (biology)
  • evolution strategies (ESs)
  • exploration
  • Games
  • meta-learning
  • multiagent
  • Optimization
  • parallelism
  • Q-learning
  • Robots
  • Scalability

Fingerprint

Dive into the research topics of 'Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey'. Together they form a unique fingerprint.

Cite this