Abstract
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.
Abstract (translated)
尽管强化学习最近取得了巨大的成功,但这种试错学习在复杂环境中可能是不实用的或效率不高的。另一方面,使用演示可以使代理从专家知识中获得利益,而不是必须通过探索发现最佳行动。在本调查中,我们讨论了在顺序决策中使用演示的优缺点,以及在基于学习的决策范式中(例如,在学习模型中的强化学习和规划)使用演示的各种方法,并讨论了在各种情况下收集演示的方法。此外,我们示例了一个实用的管道,用于在最近提出的ManiSkill机器人学习基准中生成和利用演示。
URL
https://arxiv.org/abs/2303.13489