arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.05022cs.LGcs.AI
收藏

推箱子中基于潜能的奖励塑造

Potential-based Reward Shaping in Sokoban

Leiden University(莱顿大学)

Zhao Yang, Mike Preuss, Aske Plaat

摘要:

学习解决稀疏奖励强化学习问题是困难的,因为缺乏对目标的指导。但在某些问题中,先验知识可以用来增强学习过程。奖励塑造是一种将先验知识融入到原始奖励函数中以加快学习速度的方法。虽然以前的工作已经调查了使用专家知识来生成潜在的功能,在这项工作中,我们研究是否可以使用搜索算法(A*)自动生成一个潜在的功能,奖励塑造推箱子,一个著名的规划任务。结果表明,使用成形奖励函数学习比从头开始学习更快。我们的研究结果表明,距离函数可能是一个合适的函数推箱子。这项工作证明了解决多个实例的帮助下,奖励塑造的可能性。结果可以被压缩成一个单一的策略,这可以被看作是训练一个能够解决看不见的实例的通用策略的第一阶段。

英文摘要:

Learning to solve sparse-reward reinforcement learning problems is difficult, due to the lack of guidance towards the goal. But in some problems, prior knowledge can be used to augment the learning process. Reward shaping is a way to incorporate prior knowledge into the original reward function in order to speed up the learning. While previous work has investigated the use of expert knowledge to generate potential functions, in this work, we study whether we can use a search algorithm(A*) to automatically generate a potential function for reward shaping in Sokoban, a well-known planning task. The results showed that learning with shaped reward function is faster than learning from scratch. Our results indicate that distance functions could be a suitable function for Sokoban. This work demonstrates the possibility of solving multiple instances with the help of reward shaping. The result can be compressed into a single policy, which can be seen as the first phrase towards training a general policy that is able to solve unseen instances.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑