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 2203.13573cs.LGcs.AIcs.NE
收藏

基于槽的Transformers时态抽象的无监督学习

Unsupervised Learning of Temporal Abstractions with Slot-based Transformers

The Swiss AI Lab (IDSIA), USI & SUPSI(瑞士人工智能实验室(IDSIA),瑞士意大利语区大学与瑞士南部应用科学与艺术大学);King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学(KAUST));Google Research(谷歌研究院)

Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber, Sjoerd van Steenkiste

摘要:

可重用子例程的发现简化了复杂强化学习问题中的决策和规划。以前的方法建议通过观察从执行策略中收集的状态-动作轨迹,以纯粹无监督的方式学习这种时间抽象。然而,目前的限制是,他们处理每个轨迹在一个完全顺序的方式,这使得他们无法修改早期的决定,根据新的传入信息的子程序边界点。在这项工作中,我们提出了SloTTAr,一个完全并行的方法,集成了序列处理Transformers与插槽注意力模块和自适应计算学习的数量,这样的子程序在一个无监督的方式。我们展示了SloTTAr如何能够在边界点发现方面超越强基线,即使对于包含可变数量的子例程的序列,同时在现有基准上的训练速度快7倍。

英文摘要:

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing state-action trajectories gathered from executing a policy. However, a current limitation is that they process each trajectory in an entirely sequential manner, which prevents them from revising earlier decisions about sub-routine boundary points in light of new incoming information. In this work we propose SloTTAr, a fully parallel approach that integrates sequence processing Transformers with a Slot Attention module and adaptive computation for learning about the number of such sub-routines in an unsupervised fashion. We demonstrate how SloTTAr is capable of outperforming strong baselines in terms of boundary point discovery, even for sequences containing variable amounts of sub-routines, while being up to 7x faster to train on existing benchmarks.

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。

↑