ReinFlow
ReinFlow combines Flow Policy with online reinforcement learning for fine-tuning across various robotic tasks.
GraphCanon updated 4w · GitHub synced 4w · 29 views this month
Decision brief
Integrates flow-based models with reinforcement learning for robotics tasks
Good fit when
- Need to fine-tune policies in robotic manipulation or locomotion
- Wishing to apply variability-informed algorithms like Pi0 and GR00TN1.5
Avoid when
- Looking for solutions outside of robotic control tasks
- Requiring offline reinforcement learning methods instead
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (91d since push)
- As of 4w
- Provenance
- Not a fork · Personal account
- As of 4w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install ReinFlowSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
An open-source project that integrates flow-based models with reinforcement learning techniques to enhance policy tuning in robotics and visuomotor control tasks such as locomotion and manipulation, supporting variability-informed algorithms like Pi0 and GR00TN1.5.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Jul 25, 2026
Categories
Tags
README
:rocket: Installation
Please follow the steps in installation/reinflow-setup.md.
:rocket: Quick Start: Reproduce Our Results
To fully reproduce our experiments, please refer to ReproduceExps.md.
To download our training data and reproduce the plots in the paper, please refer to ReproduceFigs.md.
License
This repository is released under the MIT license. See LICENSE. If you use our code, we appreciate it if you paste the license at the beginning of the script.
For agents
This page has a .md twin and JSON over the API.