arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.08070cs.RO
收藏

无需在线探索即可学习稳健的驾驶策略

Learning robust driving policies without online exploration

Daniel Graves, Nhat M. Nguyen, Kimia Hassanzadeh, Jun Jin, Jun Luo

摘要:

我们提出了一种多时间尺度的预测表示学习方法,以离线方式有效地学习鲁棒的驾驶策略,该方法可以很好地推广到新的道路几何形状,以及离线训练数据中未覆盖的损坏和分散注意力的车道条件。我们表明,我们提出的表示学习方法可以很容易地应用于离线(批处理)强化学习设置,展示了在新的条件下,与标准批处理RL方法相比,能够很好地和有效地推广。我们提出的方法利用了在现实世界中完全离线收集的训练数据,这消除了深入的在线探索的需要,这些探索阻碍了在现实世界的机器人训练中应用深度强化学习。为了评估和分析我们提出的索赔,在模拟器和真实世界的情况下进行了各种实验。

英文摘要:

We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are not covered in the offline training data. We show that our proposed representation learning method can be applied easily in an offline (batch) reinforcement learning setting demonstrating the ability to generalize well and efficiently under novel conditions compared to standard batch RL methods. Our proposed method utilizes training data collected entirely offline in the real-world which removes the need of intensive online explorations that impede applying deep reinforcement learning on real-world robot training. Various experiments were conducted in both simulator and real-world scenarios for the purpose of evaluation and analysis of our proposed claims.

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。

↑