Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery. (arXiv:2210.03516v1 [cs.NE])

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for
training neural policies to solve complex control tasks. However, these
policies tend to be overfit to the exact specifications of the task and
environment they were trained on, and thus do not perform well when conditions
deviate slightly or when composed hierarchically to solve even more complex
tasks. Recent work has shown that training a mixture of policies, as opposed to
a single one, that are driven to explore …

arxiv discovery neuroevolution reinforcement reinforcement learning