# Toward Deployable Multi-Robot Collaboration via a Symbolically-Guided Decision Transformer

arXiv: https://arxiv.org/abs/2508.13877 · HTML: https://mlsanity.com/paper/2508.13877/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Placed in

- Offline RL and imitation learning from data / [Decision transformers and sequence modeling](https://mlsanity.com/offlinerl/decision-transformers-and-sequence-modeling/)

## Builds on (most cited first, 4 of 4)

- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Rapid Locomotion via Reinforcement Learning](https://mlsanity.com/paper/2205.02824/) (2022)
- [Robotic Grasping using Deep Reinforcement Learning](https://mlsanity.com/paper/2007.04499/) (2020)
- [Deep Reinforcement Learning for Robotic Pushing and Picking in Cluttered Environment](https://mlsanity.com/paper/2302.10717/) (2023)

## Abstract (arXiv)

Reinforcement learning (RL) has demonstrated great potential in robotic operations. However, its data-intensive nature and reliance on the Markov Decision Process (MDP) assumption limit its practical deployment in real-world scenarios involving complex dynamics and long-term temporal dependencies, such as multi-robot manipulation. Decision Transformers (DTs) have emerged as a promising offline alternative by leveraging causal transformers for sequence modeling in RL tasks. However, their applications to multi-robot manipulations still remain underexplored. To address this gap, we propose a novel framework, Symbolically-Guided Decision Transformer (SGDT), which integrates a neuro-symbolic mechanism with a causal transformer to enable deployable multi-robot collaboration. In the proposed SGDT framework, a neuro-symbolic planner generates a high-level task-oriented plan composed of symbolic subgoals. Guided by these subgoals, a goal-conditioned decision transformer (GCDT) performs low-level sequential decision-making for multi-robot manipulation. This hierarchical architecture enables structured, interpretable, and generalizable decision making in complex multi-robot collaboration tasks. We evaluate the performance of SGDT across a range of task scenarios, including zero-shot and few-shot scenarios. To our knowledge, this is the first work to explore DT-based technology for multi-robot manipulation.