RMTL: Reinforced Micro-task Learning for Long-Horizon Manipulation with VLM Rewards
This paper proposes RMTL (Reinforced Micro-task Learning), which decomposes long-horizon manipulation tasks into language-described micro-tasks and trains an agent to switch between them. Using multi-view VLM rewards, reverse curriculum, and a hierarchical policy, RMTL provides more informative reward signals than single-prompt VLM rewards, enabling faster learning. Experiments on the Fetch manipulation environment validate its effectiveness.
[2606.26175] RMTL: Reinforced Micro-task Learning for Long-Horizon Manipulation with VLM Rewards
[Submitted on 24 Jun 2026]
Title:RMTL: Reinforced Micro-task Learning for Long-Horizon Manipulation with VLM Rewards
View a PDF of the paper titled RMTL: Reinforced Micro-task Learning for Long-Horizon Manipulation with VLM Rewards, by An{\i}l Can Ate\c{s} and 2 other authors
View PDF HTML (experimental)
Abstract:Reinforcement learning (RL) for robotic manipulation often requires manually designing a dense reward function, which is difficult to tune and often fragile, or learning a reward from human demonstrations or preferences, which can be expensive. A recent line of work uses pretrained vision-language models (VLMs) as zero-shot reward models, replacing these costs with a single text prompt. However, we argue that a single global prompt is too coarse for long-horizon manipulation tasks with randomized initial conditions. The single-prompt VLM reward is near-flat for much of the trajectory, making early progress hard for the agent to detect. We propose Reinforced Micro-Task Learning (RMTL), an approach that decomposes a manipulation task into a small set of language-described micro-tasks and trains the agent to switch between them. At each step, the agent receives a multi-view VLM reward computed using the prompt of the currently active micro-task and averaged across multiple camera views to reduce the effect of view-specific occlusions. A reverse curriculum gradually exposes the agent to harder initial conditions, while a PPO worker is first trained with a fixed distance-based rule that selects the active micro-task. We then replace this rule with a learned hierarchical manager, turning rule-based phase selection into a fully learned hierarchical policy. We instantiate RMTL on the Fetch manipulation environment using three short stage-specific prompts and without additional prompt tuning. Experiments show that RMTL provides more informative reward signals than single-prompt VLM rewards, enabling faster learning. These results suggest that decomposing VLM rewards into micro-task-specific language prompts can substantially improve the scalability of language-guided reinforcement learning for robotic manipulation.
Comments: 16 pages, 11 figures
Subjects:
Robotics (cs.RO)
Cite as: arXiv:2606.26175 [cs.RO]
(or arXiv:2606.26175v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.26175
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Cihan Topal [view email] [v1] Wed, 24 Jun 2026 10:32:48 UTC (5,280 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled RMTL: Reinforced Micro-task Learning for Long-Horizon Manipulation with VLM Rewards, by An{\i}l Can Ate\c{s} and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)