On the Benefit of Optimal Transport for Curriculum Reinforcement Learning

arXiv:2309.14091v2 Announce Type: replace
Abstract: Curriculum reinforcement learning (CRL) allows solving complex tasks by generating a tailored sequence of learning tasks, starting from easy ones and subsequently increasing their difficulty. Although the potential of curricula in RL has been clearly shown in various works, it is less clear how to generate them for a given learning environment, resulting in various methods aiming to automate this task. In this work, we focus on framing curricula as interpolations between task distributions, which …

abstract arxiv benefit clear cs.lg curriculum easy ones reinforcement reinforcement learning tasks transport type