Saved in:
Bibliographic Details
Main Authors: Wang, Yongyi, Liu, Hanyu, Li, Lingfeng, Chen, Bozhou, Li, Ang, Zheng, Qirui, Yang, Xionghui, Wang, Chucai, Li, Wenxin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.06104
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915989322465280
author Wang, Yongyi
Liu, Hanyu
Li, Lingfeng
Chen, Bozhou
Li, Ang
Zheng, Qirui
Yang, Xionghui
Wang, Chucai
Li, Wenxin
author_facet Wang, Yongyi
Liu, Hanyu
Li, Lingfeng
Chen, Bozhou
Li, Ang
Zheng, Qirui
Yang, Xionghui
Wang, Chucai
Li, Wenxin
contents Decision Transformer (DT) formulates offline reinforcement learning as autoregressive sequence modeling, achieving promising results by predicting actions from a sequence of Return-to-Go (RTG), state, and action tokens. However, RTG is a scalar that summarizes future rewards, containing far less information than typical state or action vectors, yet it consumes the same computational budget per token. Worse, the self-attention cost of Transformers grows quadratically with sequence length, so including RTG as a separate token adds unnecessary overhead. We propose SlimDT, which removes RTG from the autoregressive sequence. Instead, we inject RTG information into the state representations before the sequential modeling step, allowing the Transformer to process only a compact (state, action) sequence. This reduces the sequence length by one-third, directly improving inference efficiency. On the D4RL benchmark, SlimDT surpasses standard DT across various tasks and achieves performance comparable to existing state-of-the-art methods. Decoupling a sparse conditioning signal from an information-rich sequence thus yields both computational gains and higher task performance.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06104
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer
Wang, Yongyi
Liu, Hanyu
Li, Lingfeng
Chen, Bozhou
Li, Ang
Zheng, Qirui
Yang, Xionghui
Wang, Chucai
Li, Wenxin
Machine Learning
Artificial Intelligence
Decision Transformer (DT) formulates offline reinforcement learning as autoregressive sequence modeling, achieving promising results by predicting actions from a sequence of Return-to-Go (RTG), state, and action tokens. However, RTG is a scalar that summarizes future rewards, containing far less information than typical state or action vectors, yet it consumes the same computational budget per token. Worse, the self-attention cost of Transformers grows quadratically with sequence length, so including RTG as a separate token adds unnecessary overhead. We propose SlimDT, which removes RTG from the autoregressive sequence. Instead, we inject RTG information into the state representations before the sequential modeling step, allowing the Transformer to process only a compact (state, action) sequence. This reduces the sequence length by one-third, directly improving inference efficiency. On the D4RL benchmark, SlimDT surpasses standard DT across various tasks and achieves performance comparable to existing state-of-the-art methods. Decoupling a sparse conditioning signal from an information-rich sequence thus yields both computational gains and higher task performance.
title Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.06104