Back to Search Start Over

Pearl: Parallel Evolutionary and Reinforcement Learning Library

Authors :
Tangri, Rohan
Mandic, Danilo P.
Constantinides, Anthony G.
Publication Year :
2022

Abstract

Reinforcement learning is increasingly finding success across domains where the problem can be represented as a Markov decision process. Evolutionary computation algorithms have also proven successful in this domain, exhibiting similar performance to the generally more complex reinforcement learning. Whilst there exist many open-source reinforcement learning and evolutionary computation libraries, no publicly available library combines the two approaches for enhanced comparison, cooperation, or visualization. To this end, we have created Pearl (https://github.com/LondonNode/Pearl), an open source Python library designed to allow researchers to rapidly and conveniently perform optimized reinforcement learning, evolutionary computation and combinations of the two. The key features within Pearl include: modular and expandable components, opinionated module settings, Tensorboard integration, custom callbacks and comprehensive visualizations.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2201.09568
Document Type :
Working Paper