arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.02970cs.LGcs.AIcs.RO
收藏

闭环深度学习:使用反向传播生成前向模型

Closed-loop deep learning: generating forward models with back-propagation

University of Glasgow(格拉斯哥大学)

Sama Daryanavard, Bernd Porr

摘要:

反射是一种简单的闭环控制方法,它试图最大限度地减少错误,但由于总是反应太晚而无法做到这一点。自适应算法可以使用该误差来在预测线索的帮助下学习前向模型。例如,驾驶员学会通过向前看来改善他们的转向,以避免在最后一分钟转向。为了处理复杂的线索,如前面的道路,深度学习是一个自然的选择。然而,这通常仅通过采用具有离散状态空间的深度强化学习来间接实现。在这里,我们展示了如何通过将深度学习嵌入到闭环系统中并保持其连续处理来直接实现这一点。我们具体展示了如何在z空间中实现误差反向传播,以及如何在这种闭环情况下分析基于梯度的方法。这种学习模式的性能证明使用线跟随器在模拟和一个真正的机器人,表现出非常快速和连续的学习。

英文摘要:

A reflex is a simple closed loop control approach which tries to minimise an error but fails to do so because it will always react too late. An adaptive algorithm can use this error to learn a forward model with the help of predictive cues. For example a driver learns to improve their steering by looking ahead to avoid steering in the last minute. In order to process complex cues such as the road ahead deep learning is a natural choice. However, this is usually only achieved indirectly by employing deep reinforcement learning having a discrete state space. Here, we show how this can be directly achieved by embedding deep learning into a closed loop system and preserving its continuous processing. We show specifically how error back-propagation can be achieved in z-space and in general how gradient based approaches can be analysed in such closed loop scenarios. The performance of this learning paradigm is demonstrated using a line-follower both in simulation and on a real robot that show very fast and continuous learning.

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。

↑