QF3: Fast Flow RL with Filtered Q-Gradients

Chung Min Kim; Brent Yi; David McAllister; Hongsuk Choi; Himanshu Gaurav Singh; Jinkun Cao; Ken Goldberg; Pieter Abbeel; Carmelo Sferrazza; Angjoo Kanazawa

arXiv · 2610.08789

QF3: Fast Flow RL with Filtered Q-Gradients

Chung Min Kim·Brent Yi·David McAllister·Hongsuk Choi·Himanshu Gaurav Singh·Jinkun Cao·Ken Goldberg·Pieter Abbeel·Carmelo Sferrazza·Angjoo Kanazawa

View original source ↗Read source document ↗Export metadata ↓

Abstract

Flow policies have become a standard policy class for learning robot behaviors from demonstrations, but reinforcement learning is still critical for improving pre-trained flow policies or learning them from scratch through interaction. We introduce QF3 (Fast Flow RL with Filtered Q-Gradients), an online off-policy RL algorithm that trains a flow policy with flow matching plus the critic's action gradient, backpropagated through a one-step prediction of the flow's output. To keep updates where the critic and this prediction are reliable, QF3 applies the critic gradient only to action dimensions that stay near the replay action. To our knowledge, QF3 is the first off-policy flow RL method to train humanoid locomotion policies from scratch and transfer them zero-shot to hardware. Paired with a high-throughput off-policy training recipe, it trains humanoid locomotion and motion-tracking policies with a 10x wall-clock speedup over FPO++, a recent on-policy flow RL method. We further apply QF3 to fine-tune pretrained flow-based manipulation policies on both ABC-Sim and Robomimic tasks. These results suggest that QF3 can both learn robot policies from scratch and refine those acquired from demonstrations. Website: https://qf3-rl.github.io/

Explore related subjects

cs.RO cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Chung Min Kim, Brent Yi, David McAllister, Hongsuk Choi, Himanshu Gaurav Singh, Jinkun Cao, Ken Goldberg, Pieter Abbeel, Carmelo Sferrazza, Angjoo Kanazawa. 2026-10-06. QF3: Fast Flow RL with Filtered Q-Gradients. https://arxiv.org/abs/2610.08789

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction

Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations into control actions. However, existing VLAs are primarily trained on successful expert demonstrations and lack structured supervision for failure diagnosis and recovery, limiting robustness in open-world scenarios. To address this limitation, we propose the Robotic Failure Analysis and Correction (RoboFAC) framework. We construct a large-scale failure-centric dataset comprising 9,440 erroneous manipulation trajectories and 78,623 QA pairs across 53 scenes in both simulation and real-world environments, with systematically categorized failure types. Leveraging this dataset, we develop a lightweight multimodal model specialized for task understanding, failure analysis, and failure correction, enabling efficient local deployment while remaining competitive with large proprietary models. Experimental results demonstrate that RoboFAC achieves a 34.1% higher failure analysis accuracy compared to GPT-4o. Furthermore, we integrated RoboFAC as an external supervisor in a real-world VLA control pipeline, yielding a 29.1% relative improvement across four tasks while significantly reducing latency relative to GPT-4o. These results demonstrate that RoboFAC enables systematic failure diagnosis and recovery, significantly enhancing VLA recovery capabilities. Our model and dataset are publicly available at https://github.com/MINT-SJTU/RoboFAC.

cs.RO↗

arXiv2026

Agentic Scene Policies

Designing or learning robot policies that generalize zero-shot across a range of language instructions and objects is a core problem in robotics. Vision-Language-Action models (VLAs) learn such policies end-to-end by repurposing existing Vision-Language Models (VLMs), but generalization to new instructions and objects remains challenging. An alternative is to implement a modular policy by leveraging an explicit VLM-based 3D scene representation and motion planning. While modular policies show strong zero-shot potential, they typically retrieve objects based on semantics without explicit spatial reasoning, severely restricting their overall grounding capabilities. They also interact with objects using basic grasping and navigation skills. In this work, we address these limitations by unifying grounding capabilities and robot skills in a single agentic action space through a scene-agent tool interface. By leveraging part-level affordances, our skills generalize across diverse objects and enable zero-shot interactions such as unplugging chargers and opening drawers. We name the resulting framework Agentic Scene Policies (ASP). Through extensive real-world experiments, we show how ASP consistently outperforms leading VLAs in the zero-shot setting. We also demonstrate the extensibility of our framework by introducing a mobile version of ASP to tackle room-level queries. See our project page (https://montrealrobotics.ca/agentic-scene-policies.github.io/) for more results.

cs.RO↗

arXiv2026

RoboPilot: Generalizable Dynamic Robotic Manipulation with Dual-thinking Modes

Despite rapid progress in robotics, complex or long-horizon tasks remain a fundamental challenge. Most current approaches follow an open-loop paradigm with limited reasoning and no feedback, resulting in poor robustness to environmental changes and severe error accumulation. We present RoboPilot, a dual-thinking closed-loop agentic framework for robotic manipulation that supports adaptive reasoning for complex tasks in real-world dynamic environments. RoboPilot leverages primitive actions for structured task planning and flexible action generation as a agentic system, while introducing feedback to enable replanning from dynamic changes and execution errors. Chain-of-Thought reasoning further enhances high-level task planning and guides low-level action generation. The agentic system dynamically switches between fast and slow thinking to balance efficiency and accuracy. To systematically evaluate the robustness of RoboPilot in diverse robot manipulation scenarios, we introduce RoboPilot-Bench, a benchmark spanning 21 tasks across 10 categories, including infeasible-task recognition and dynamic recovery. Experiments show that RoboPilot outperforms state-of-the-art baselines by 11% in task success rate, and the real-world deployment on an industrial robot further demonstrates its robustness.

cs.RO↗