Pearl: Parallel Evolutionary and Reinforcement Learning Library
This provides a tool for researchers to compare and combine reinforcement learning and evolutionary methods, but it is incremental as it builds on existing libraries without new algorithmic breakthroughs.
The authors tackled the lack of a combined library for reinforcement learning and evolutionary computation by creating Pearl, an open-source Python library that enables optimized and rapid experimentation with these approaches, featuring modular components, Tensorboard integration, and visualizations.
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.