We show that achieving trajectory stitching is possible without explicitly training Decision Transformer (DT) to stitch.
A key insight is that DT can be utilized to stitch by adjusting the history length maintained in DT.
Given two trajectories
We propose an architecture that approximate the maximum value of in-support return
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.
Multi-game Atari results. The proposed EDT improves the performance of DT by 39.8%. We consider 20 Atari games for the multi-game setting.
Multi-task D4RL results. The proposed EDT outperform the baseline methods by a large margin in a multi-task setting. We gather medium-replay datasets from the four tasks as a single dataset for training. The medium-replay datasets contain trajectories collected from random policies, which makes it challenging for non-stitching methods.
The figure illustrates the action inference procedure within the proposed Elastic Decision Transformer.
Initially, we estimate the value maximizer,
@article{wu2023elastic,
author={Wu, Yueh-Hua and Wang, Xiaolong and Hamaya, Masashi},
title={Elastic Decision Transformer},
archivePrefix = {arXiv},
eprint = {2307.02484},
primaryClass = {cs.LG},
year={2023},
}