Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning

arXiv:2405.03379v1 Announce Type: new
Abstract: Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data that is difficult to obtain, especially for domains such as robotics. Our approach consists of a reverse curriculum followed by a forward curriculum. Unique …

abstract arxiv cs.ai cs.lg cs.ro curriculum curriculum learning data efficiency environment framework learn offline policies reinforcement reinforcement learning sample solve tasks through type