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 1507.04888cs.LG
收藏

最大熵深度逆强化学习

Maximum Entropy Deep Inverse Reinforcement Learning

University of Oxford(牛津大学)

Markus Wulfmeier, Peter Ondruska, Ingmar Posner

摘要:

本文提出了一个通用的框架,利用神经网络的代表能力,以近似复杂的,非线性的奖励函数的上下文中解决逆强化学习(IRL)问题。在这种情况下,我们表明,IRL的最大熵范式自然适合于深度架构的有效训练。在测试时,该方法导致独立于演示数量的计算复杂性,这使得它特别适合于终身学习场景中的应用。我们的方法实现了与现有基准的最先进水平相称的性能,同时超过了基于高度变化的奖励结构的替代基准。最后,我们扩展了基本架构-相当于宽度为1的全卷积神经网络(FCNN)的简化子类-以包括更大的卷积,以消除对预先计算的空间特征的依赖,并对原始输入表示进行处理。

英文摘要:

This paper presents a general framework for exploiting the representational capacity of neural networks to approximate complex, nonlinear reward functions in the context of solving the inverse reinforcement learning (IRL) problem. We show in this context that the Maximum Entropy paradigm for IRL lends itself naturally to the efficient training of deep architectures. At test time, the approach leads to a computational complexity independent of the number of demonstrations, which makes it especially well-suited for applications in life-long learning scenarios. Our approach achieves performance commensurate to the state-of-the-art on existing benchmarks while exceeding on an alternative benchmark based on highly varying reward structures. Finally, we extend the basic architecture - which is equivalent to a simplified subclass of Fully Convolutional Neural Networks (FCNNs) with width one - to include larger convolutions in order to eliminate dependency on precomputed spatial features and work on raw input representations.

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。

↑