Multitask Neuroevolution for Reinforcement Learning with Long and Short Episodes. (arXiv:2203.10844v3 [cs.NE] UPDATED)

Studies have shown evolution strategies (ES) to be a promising approach for
reinforcement learning (RL) with deep neural networks. However, the issue of
high sample complexity persists in applications of ES to deep RL over long
horizons. This paper is the first to address the shortcoming of today's methods
via a novel neuroevolutionary multitasking (NuEMT) algorithm, designed to
transfer information from a set of auxiliary tasks (of short episode length) to
the target (full length) RL task at hand. The …

arxiv episodes neuroevolution reinforcement reinforcement learning