arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2307.02484cs.LGcs.AI
收藏

弹性决策Transformer

Elastic Decision Transformer

OMRON SINIC X(欧姆龙 SINIC X 研究院);UC San Diego(加州大学圣地亚哥分校)

Yueh-Hua Wu, Xiaolong Wang, Masashi Hamaya

摘要:

本文介绍了弹性决策Transformer(EDT),一个显着的进步,现有的决策Transformer(DT)及其变种。虽然DT声称生成最佳轨迹,但经验证据表明它难以进行轨迹拼接,这是一个涉及从一组次优轨迹的最佳部分生成最佳或接近最佳轨迹的过程。建议的EDT区分自己的动作推理在测试时,通过调整DT中保持的历史长度来实现的轨迹拼接。此外,EDT通过在先前轨迹是最佳的时保留较长的历史并且在先前轨迹是次最佳的时保留较短的历史来优化轨迹,从而使其能够与更佳的轨迹"缝合"。大量的实验表明,EDT有能力弥合基于DT和基于Q学习的方法之间的性能差距。特别是,EDT在D4RL运动基准和Atari游戏的多任务机制中优于基于Q学习的方法。视频请访问:www.example.com

英文摘要:

This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT purports to generate an optimal trajectory, empirical evidence suggests it struggles with trajectory stitching, a process involving the generation of an optimal or near-optimal trajectory from the best parts of a set of sub-optimal trajectories. The proposed EDT differentiates itself by facilitating trajectory stitching during action inference at test time, achieved by adjusting the history length maintained in DT. Further, the EDT optimizes the trajectory by retaining a longer history when the previous trajectory is optimal and a shorter one when it is sub-optimal, enabling it to "stitch" with a more optimal trajectory. Extensive experimentation demonstrates EDT's ability to bridge the performance gap between DT-based and Q Learning-based approaches. In particular, the EDT outperforms Q Learning-based methods in a multi-task regime on the D4RL locomotion benchmark and Atari games. Videos are available at: https://kristery.github.io/edt/

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。

↑