Elastic Decision Transformer

TL;DR

The Elastic Decision Transformer (EDT) enhances trajectory stitching during action inference by adjusting history length, leading to improved performance over existing methods in multi-task benchmarks like D4RL locomotion and Atari games.

Contribution

EDT introduces a novel approach to trajectory stitching by dynamically adjusting history length during inference, improving over standard Decision Transformers.

Findings

EDT outperforms Q Learning-based methods on D4RL locomotion tasks.

EDT achieves better results in Atari game benchmarks.

Trajectory stitching improves with dynamic history adjustment.

Abstract

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/