Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey
This is an incremental survey paper that synthesizes existing knowledge for researchers in machine learning and AI.
This paper provides a comparative analysis of Deep Reinforcement Learning (DRL) and Evolution Strategies (ESs) in sequential decision-making problems, highlighting their strengths, weaknesses, and the benefits of hybrid approaches.
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 multi-agent learning. Then, the benefits of hybrid algorithms that combine concepts from DRL and ESs are highlighted. Finally, to have an indication about how they compare in real-world applications, a survey of the literature for the set of applications they support is provided.