# Human-in-the-loop Online Rejection Sampling for Robotic Manipulation

arXiv: https://arxiv.org/abs/2510.26406 · HTML: https://mlsanity.com/paper/2510.26406/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 31 of its 35 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 31)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [Flow Q-Learning](https://mlsanity.com/paper/2502.02538/) (2025)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://mlsanity.com/paper/2309.02473/) (2023)
- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024)
- [Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions](https://mlsanity.com/paper/2309.10150/) (2023)
- [A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation](https://mlsanity.com/paper/2507.05331/) (2025)
- [Improving Vision-Language-Action Model with Online Reinforcement Learning](https://mlsanity.com/paper/2501.16664/) (2025)
- [Human-in-the-Loop Imitation Learning using Remote Teleoperation](https://mlsanity.com/paper/2012.06733/) (2020)
- [Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment](https://mlsanity.com/paper/2211.08416/) (2022)
- [Reinforcement Learning with Action Chunking](https://mlsanity.com/paper/2507.07969/) (2025)
- [Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone](https://mlsanity.com/paper/2412.06685/) (2024)
- [RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction](https://mlsanity.com/paper/2509.07953/) (2025)

## Built on by (most cited first, 5 of 5)

- [UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation](https://mlsanity.com/paper/2605.10821/) (2026)
- [IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2602.20715/) (2026)
- [OMP: One-step Meanflow Policy with Directional Alignment](https://mlsanity.com/paper/2512.19347/) (2025)
- [Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2608.16843/) (2026)
- [No Free Checker: A Survey of Verifiers for Robot Policies](https://mlsanity.com/paper/2609.09250/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate steps. In contrast, imitation learning (IL) is easy to train but often underperforms due to its offline nature. In this paper, we propose Hi-ORS, a simple yet effective post-training method that utilizes rejection sampling to achieve both training stability and high robustness. Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning, and adopts a reward-weighted supervised training objective to provide dense intermediate-step supervision. For systematic study, we develop an asynchronous inference-training framework that supports flexible online human-in-the-loop corrections, which serve as explicit guidance for learning error-recovery behaviors. Across three real-world tasks and two embodiments, Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training, outperforming RL and IL baselines by a substantial margin in both effectiveness and efficiency. Notably, the fine-tuned policy exhibits strong test-time scalability by reliably executing complex error-recovery behaviors to achieve better performance.