arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15588cs.LGcs.AIcs.ROstat.ML
收藏

数据高效的后见之明政策外选项学习

Data-efficient Hindsight Off-policy Option Learning

DeepMind(深度思维)

Markus Wulfmeier, Dushyant Rao, Roland Hafner, Thomas Lampe, Abbas Abdolmaleki, Tim Hertweck, Michael Neunert, Dhruva Tirumala, Noah Siegel, Nicolas Heess, Martin Riedmiller

摘要:

本文介绍了一种数据有效的期权学习算法--后见之明的非策略期权(HO 2)。给定任何轨迹,HO 2推断可能的选项选择,并通过动态规划推断过程反向传播,以稳健地训练所有策略组件脱离策略和端到端。该方法优于现有的选项学习方法的共同基准。为了更好地理解的选项框架,并从时间和动作抽象的好处,我们评估消融与平面政策和混合政策具有可比的优化。结果突出了这两种类型的抽象以及离线训练和信任区域约束的重要性,特别是在具有挑战性的模拟3D机器人操作任务中。最后,我们直观地调整推理步骤,以研究增加时间抽象对使用预训练选项和从头开始训练的影响。

英文摘要:

We introduce Hindsight Off-policy Options (HO2), a data-efficient option learning algorithm. Given any trajectory, HO2 infers likely option choices and backpropagates through the dynamic programming inference procedure to robustly train all policy components off-policy and end-to-end. The approach outperforms existing option learning methods on common benchmarks. To better understand the option framework and disentangle benefits from both temporal and action abstraction, we evaluate ablations with flat policies and mixture policies with comparable optimization. The results highlight the importance of both types of abstraction as well as off-policy training and trust-region constraints, particularly in challenging, simulated 3D robot manipulation tasks from raw pixel inputs. Finally, we intuitively adapt the inference step to investigate the effect of increased temporal abstraction on training with pre-trained options and from scratch.

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。

↑