TechRxiv
DRL_vs_ESs.pdf (1.58 MB)
Download file

Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

Download (1.58 MB)
preprint
posted on 29.09.2021, 21:32 authored by Amjad Yousef Majid, Serge Saaybi, Tomas van Rietbergen, Vincent Francois-Lavet, R Venkatesha Prasad, Chris Verhoeven
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.

History

Email Address of Submitting Author

a.y.majid@tudelft.nl

Submitting Author's Institution

Delft University of Technology

Submitting Author's Country

Netherlands