Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit from expert knowledge rather than having to discover the best action to take through exploration. In this survey, we discuss the advantages of using demonstrations in sequential decision making, various ways to apply demonstrations in learning-based decision making paradigms (for example, reinforcement learning and planning in the learned models), and how to collect the demonstrations in various scenarios. Additionally, we exemplify a practical pipeline for generating and utilizing demonstrations in the recently proposed ManiSkill robot learning benchmark.

翻译：尽管强化学习近年来取得了巨大成功，但这种试错学习在复杂环境中可能不切实际或效率低下。另一方面，利用示范使智能体能够从专家知识中受益，而无需通过探索来发现最佳行动。在本综述中，我们讨论了在序贯决策中使用示范的优势、在基于学习的决策范式（例如，强化学习及基于所学模型进行规划）中应用示范的各种方法，以及在不同场景下如何收集示范。此外，我们以近期提出的ManiSkill机器人学习基准为例，展示了一个生成和利用示范的实用流程。