arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.04419cs.AI
收藏

部分可观测马尔可夫决策过程中的深度分层强化学习算法

Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes

Kyung Hee University(庆熙大学);Queen’s University Belfast(贝尔法斯特女王大学)

Le Pham Tuyen, Ngo Anh Vien, Abu Layek, TaeChoong Chung

AI总结:

针对分层结构任务中平面强化学习效果差、效率低,且现实任务多为部分可观测的问题,提出可同时适用于MDP和POMDP的深度分层强化学习算法,并在多种挑战性分层POMDP任务上开展评估。

摘要:

近年来,随着深度学习技术的广泛应用与计算能力的快速提升,强化学习已取得诸多显著成果。然而众所周知,平面强化学习算法在具有分层结构的任务(例如包含多个子任务的任务)中往往难以实现良好的学习效果与数据效率。分层强化学习是应对这类挑战性任务的一种系统化方法。另一方面,许多现实世界的任务通常仅具备部分可观测性,其中状态测量往往是不完善的、仅部分可观测的。这类场景下的强化学习问题可建模为部分可观测马尔可夫决策过程(POMDP)。本文研究任务同时具备部分可观测性与分层属性的POMDP场景下的分层强化学习问题。我们提出一种用于分层POMDP学习的深度分层强化学习方法,该深度分层强化学习算法可同时应用于MDP和POMDP学习。我们在多种具有挑战性的分层POMDP任务上对所提算法进行了评估。

英文摘要:

In recent years, reinforcement learning has achieved many remarkable successes due to the growing adoption of deep learning techniques and the rapid growth in computing power. Nevertheless, it is well-known that flat reinforcement learning algorithms are often not able to learn well and data-efficient in tasks having hierarchical structures, e.g. consisting of multiple subtasks. Hierarchical reinforcement learning is a principled approach that is able to tackle these challenging tasks. On the other hand, many real-world tasks usually have only partial observability in which state measurements are often imperfect and partially observable. The problems of RL in such settings can be formulated as a partially observable Markov decision process (POMDP). In this paper, we study hierarchical RL in POMDP in which the tasks have only partial observability and possess hierarchical properties. We propose a hierarchical deep reinforcement learning approach for learning in hierarchical POMDP. The deep hierarchical RL algorithm is proposed to apply to both MDP and POMDP learning. We evaluate the proposed algorithm on various challenging hierarchical POMDP.

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。

↑