arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09439cs.LGcs.AIcs.NEstat.ML
收藏

潜在表示预测网络

Latent Representation Prediction Networks

Institut für Neuroinformatik, Ruhr-Universität Bochum(波鸿鲁尔大学神经科学研究所)

Hlynur Davíð Hlynsson, Merlin Schüler, Robin Schiewer, Tobias Glasmachers, Laurenz Wiskott

摘要:

深度学习的规划方法通常基于为不相关任务优化的学习表示。例如,他们可以接受重建环境的培训。然后,将这些表示与预测器函数相结合,以模拟卷展栏,从而在环境中导航。我们发现这种学习表示的原则并不令人满意,并建议学习它们,以便它们直接针对手头的任务进行优化:最大限度地预测预测函数。这导致了通过设计对于规划的下游任务是最优的表示,其中学习的预测器函数被用作前向模型。为此,我们提出了一种联合学习这种表示和预测函数的新方法,我们称之为潜在表示预测网络(LARP)。预测函数用作视点匹配任务中在图上搜索的前向模型,并且发现学习以最大化可预测性的表示优于预先训练的表示。我们的方法被证明是更有效的样本比标准的强化学习方法和我们的学习表示成功地转移到不同的对象。

英文摘要:

Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environment. These representations are then combined with predictor functions for simulating rollouts to navigate the environment. We find this principle of learning representations unsatisfying and propose to learn them such that they are directly optimized for the task at hand: to be maximally predictable for the predictor function. This results in representations that are by design optimal for the downstream task of planning, where the learned predictor function is used as a forward model. To this end, we propose a new way of jointly learning this representation along with the prediction function, a system we dub Latent Representation Prediction Network (LARP). The prediction function is used as a forward model for search on a graph in a viewpoint-matching task and the representation learned to maximize predictability is found to outperform a pre-trained representation. Our approach is shown to be more sample-efficient than standard reinforcement learning methods and our learned representation transfers successfully to dissimilar objects.

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。

↑