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 2006.08457cs.LGcs.AI
收藏

交互网络:使用强化学习器训练其他机器学习算法

Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms

Florian Dietz

摘要:

大脑中神经元的布线比当代人工神经网络中的连接布线更灵活。这种额外的灵活性可能对有效解决问题和学习很重要。本文介绍了交互网络。交互网络的目标是捕捉这种额外的灵活性。交互网络由传统神经网络的集合、一组存储器位置和DQN或其他强化学习器组成。DQN决定何时执行每个神经网络,以及在哪些存储器位置上执行。通过这种方式,各个神经网络可以针对不同的任务在不同的数据上进行训练。同时,个体网络的结果影响强化学习器的决策过程。这导致了一个反馈回路,允许DQN执行改进其自身决策的操作。任何现有类型的神经网络都可以在交互网络中完整地复制,只需要恒定的计算开销。然后,交互网络可以引入额外的功能来进一步提高性能。这些使得算法更加灵活和通用,但代价是更难训练。在本文中,思想实验是用来探索如何额外的能力,互动网络可以用来改善各种现有类型的神经网络。已经进行了几个实验来证明这个概念是合理的。这表明基本思想是可行的,但它们也揭示了一些传统神经网络中没有出现的挑战,这使得交互网络非常难以训练。需要进行进一步的研究来缓解这些问题。本文概述了一些有前途的研究途径,以实现这一目标。

英文摘要:

The wiring of neurons in the brain is more flexible than the wiring of connections in contemporary artificial neural networks. It is possible that this extra flexibility is important for efficient problem solving and learning. This paper introduces the Interaction Network. Interaction Networks aim to capture some of this extra flexibility. An Interaction Network consists of a collection of conventional neural networks, a set of memory locations, and a DQN or other reinforcement learner. The DQN decides when each of the neural networks is executed, and on what memory locations. In this way, the individual neural networks can be trained on different data, for different tasks. At the same time, the results of the individual networks influence the decision process of the reinforcement learner. This results in a feedback loop that allows the DQN to perform actions that improve its own decision-making. Any existing type of neural network can be reproduced in an Interaction Network in its entirety, with only a constant computational overhead. Interaction Networks can then introduce additional features to improve performance further. These make the algorithm more flexible and general, but at the expense of being harder to train. In this paper, thought experiments are used to explore how the additional abilities of Interaction Networks could be used to improve various existing types of neural networks. Several experiments have been run to prove that the concept is sound. These show that the basic idea works, but they also reveal a number of challenges that do not appear in conventional neural networks, which make Interaction Networks very hard to train. Further research needs to be done to alleviate these issues. A number of promising avenues of research to achieve this are outlined in this paper.

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。

↑