openpi-RLT is an openpi-based real-robot RL system with RL-token-guided action refinement.
☆324May 16, 2026Updated 5 months ago
Alternatives and similar repositories for openpi-RLT
Users that are interested in openpi-RLT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Open-source implementation of "RL Token: Bootstrapping Online RL with Vision-Language-Action Models"☆108Apr 16, 2026Updated 6 months ago
- ☆65Mar 24, 2026Updated 7 months ago
- ☆219Oct 4, 2026Updated last month
- We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.☆859Updated this week
- RL Token pipeline for the SO-101 arm: π0.5 fine-tuning, RL Token training, critical-phase classifier, online RL and deployment.☆95Oct 28, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- PiStar: A closed-loop robot learning framework for data collection, value labeling, and policy fine-tuning across LIBERO simulation, Pipe…☆142Oct 18, 2026Updated 3 weeks ago
- Code for kai0, including training, inference and data collection.☆453Mar 9, 2026Updated 8 months ago
- RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI☆5,633Updated this week
- A LeRobot-based reproduction of RLT, covering RL-token learning, transition-cache generation, actor-critic training, and real-robot rollo…☆155Oct 8, 2026Updated last month
- [Science Robotics 2026] Official Implementation of the paper RL-100☆396Oct 1, 2026Updated last month
- VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models☆102Updated this week
- ☆49Jul 30, 2026Updated 3 months ago
- ☆27Oct 27, 2026Updated 2 weeks ago
- ☆165Mar 31, 2026Updated 7 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆1,585Oct 27, 2025Updated last year
- Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)☆311Apr 27, 2026Updated 6 months ago
- ☆43Jul 24, 2026Updated 3 months ago
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing☆3,933Oct 31, 2026Updated last week
- [RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model☆390Jul 6, 2026Updated 4 months ago
- An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.☆787Updated this week
- ☆163Dec 2, 2025Updated 11 months ago
- ☆146Sep 24, 2026Updated last month
- [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning☆1,910Jan 6, 2026Updated 10 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- JAX Implementation for Q-Guided Flow and Common RL Baselines☆129Aug 27, 2026Updated 2 months ago
- Running VLA at 30Hz frame rate and 480Hz trajectory frequency☆641Sep 30, 2026Updated last month
- ☆521Oct 13, 2026Updated 3 weeks ago
- This is the official implementation of the paper "ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy".☆380Mar 30, 2026Updated 7 months ago
- From Vision-Language-Action Models to a Real-World Robot Learning Stack☆316Aug 4, 2026Updated 3 months ago
- ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop ph…☆353Sep 9, 2026Updated 2 months ago
- ☆130Jun 23, 2026Updated 4 months ago
- 基于pi0.5和pi0.6的论文实现的☆138Jun 3, 2026Updated 5 months ago
- Simulated experiments for "Real-Time Execution of Action Chunking Flow Policies".☆636Dec 8, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [RSS 26] Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections☆22Jun 8, 2026Updated 5 months ago
- [CoRL 2026 Spotlight] Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection☆16Oct 13, 2026Updated 3 weeks ago
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,657Aug 20, 2026Updated 2 months ago
- This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation…☆645Oct 13, 2026Updated 3 weeks ago
- Q-Estimation and Q-Gating from BC for RL☆61Sep 8, 2026Updated 2 months ago
- ☆14,604Aug 24, 2026Updated 2 months ago
- HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos☆600Nov 4, 2026Updated last week
Are these results useful?