# Less is more -- the Dispatcher/ Executor principle for multi-task Reinforcement Learning

arXiv: https://arxiv.org/abs/2312.09120 · HTML: https://mlsanity.com/paper/2312.09120/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 14 Dec 2023.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [Maximum a Posteriori Policy Optimisation](https://mlsanity.com/paper/1806.06920/) (2018)
- [Learning by Playing - Solving Sparse Reward Tasks from Scratch](https://mlsanity.com/paper/1802.10567/) (2018)
- [Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes](https://mlsanity.com/paper/2110.06192/) (2021)
- [Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring](https://mlsanity.com/paper/2106.03427/) (2021)
- [Collect & Infer -- a fresh look at data-efficient Reinforcement Learning](https://mlsanity.com/paper/2108.10273/) (2021)
- [Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives](https://mlsanity.com/paper/2003.08854/) (2020)
- [SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration](https://mlsanity.com/paper/2211.13743/) (2022)
- [Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning](https://mlsanity.com/paper/2309.07578/) (2023)

## Built on by (most cited first, 2 of 2)

- [Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust](https://mlsanity.com/paper/2410.01971/) (2024)
- [Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control](https://mlsanity.com/paper/2506.16565/) (2025)

## Abstract (arXiv)

Humans instinctively know how to neglect details when it comes to solve complex decision making problems in environments with unforeseeable variations. This abstraction process seems to be a vital property for most biological systems and helps to 'abstract away' unnecessary details and boost generalisation. In this work we introduce the dispatcher/ executor principle for the design of multi-task Reinforcement Learning controllers. It suggests to partition the controller in two entities, one that understands the task (the dispatcher) and one that computes the controls for the specific device (the executor) - and to connect these two by a strongly regularizing communication channel. The core rationale behind this position paper is that changes in structure and design principles can improve generalisation properties and drastically enforce data-efficiency. It is in some sense a 'yes, and ...' response to the current trend of using large neural networks trained on vast amounts of data and bet on emerging generalisation properties. While we agree on the power of scaling - in the sense of Sutton's 'bitter lesson' - we will give some evidence, that considering structure and adding design principles can be a valuable and critical component in particular when data is not abundant and infinite, but is a precious resource.