arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01839cs.LGcs.AIstat.ML
收藏

预期合格性跟踪

Expected Eligibility Traces

DeepMind;University College London(伦敦大学学院)

Hado van Hasselt, Sephora Madjiheurem, Matteo Hessel, David Silver, André Barreto, Diana Borsa

摘要:

如何确定哪些状态和动作对某个结果负责的问题被称为信用分配问题,并且仍然是强化学习和人工智能中的中心研究问题。资格跟踪使有效的信用分配到最近的一系列的状态和行动所经历的代理,但不是反事实的序列,也可能导致当前状态。在这项工作中,我们引入预期的资格跟踪。预期跟踪允许通过单个更新来更新可能在当前状态之前的状态和操作,即使它们在这种情况下没有这样做。我们讨论了当预期的痕迹提供的好处,在时间差学习经典(瞬时)的痕迹,并表明,有时可以实现实质性的改善。我们提供了一种方法来顺利地插入瞬时和预期的轨迹之间的一种机制,类似于自举,这将确保所得到的算法是一个严格的概括TD($λ$)。最后,我们讨论了可能的扩展和连接到相关的想法,如后继功能。

英文摘要:

The question of how to determine which states and actions are responsible for a certain outcome is known as the credit assignment problem and remains a central research question in reinforcement learning and artificial intelligence. Eligibility traces enable efficient credit assignment to the recent sequence of states and actions experienced by the agent, but not to counterfactual sequences that could also have led to the current state. In this work, we introduce expected eligibility traces. Expected traces allow, with a single update, to update states and actions that could have preceded the current state, even if they did not do so on this occasion. We discuss when expected traces provide benefits over classic (instantaneous) traces in temporal-difference learning, and show that sometimes substantial improvements can be attained. We provide a way to smoothly interpolate between instantaneous and expected traces by a mechanism similar to bootstrapping, which ensures that the resulting algorithm is a strict generalisation of TD($λ$). Finally, we discuss possible extensions and connections to related ideas, such as successor features.

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。

↑