arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.02363cs.AI
收藏

基于逻辑神经网络的外部知识强化学习

Reinforcement Learning with External Knowledge by using Logical Neural Networks

IBM Research AI(IBM研究院人工智能部门)

Daiki Kimura, Subhajit Chaudhury, Akifumi Wachi, Ryosuke Kohita, Asim Munawar, Michiaki Tatsubori, Alexander Gray

摘要:

传统的深度强化学习方法是样本效率低下的,并且通常需要在收敛之前进行大量的训练试验。由于这样的方法在不受约束的动作集上操作,它们可能导致无用的动作。最近的神经符号框架称为逻辑神经网络(LNNs)可以同时提供神经网络和符号逻辑的关键属性。LNN的功能是作为一个端到端的可微网络,最大限度地减少新的矛盾损失,学习可解释的规则。在本文中,我们利用LNN使用基本逻辑运算(如AND和NOT)定义推理图,以加快强化学习的收敛速度。具体来说,我们提出了一种集成的方法,使无模型强化学习从外部知识源在一个基于LNN的逻辑约束框架,如动作屏蔽和指南。我们的结果经验证明,我们的方法收敛速度比无模型强化学习方法,没有这样的逻辑约束。

英文摘要:

Conventional deep reinforcement learning methods are sample-inefficient and usually require a large number of training trials before convergence. Since such methods operate on an unconstrained action set, they can lead to useless actions. A recent neuro-symbolic framework called the Logical Neural Networks (LNNs) can simultaneously provide key-properties of both neural networks and symbolic logic. The LNNs functions as an end-to-end differentiable network that minimizes a novel contradiction loss to learn interpretable rules. In this paper, we utilize LNNs to define an inference graph using basic logical operations, such as AND and NOT, for faster convergence in reinforcement learning. Specifically, we propose an integrated method that enables model-free reinforcement learning from external knowledge sources in an LNNs-based logical constrained framework such as action shielding and guide. Our results empirically demonstrate that our method converges faster compared to a model-free reinforcement learning method that doesn't have such logical constraints.

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。

↑